INDEX

Explanations

proper nouns, particularly names such as "Owens" and terms related to user experience design (UX)

oai_token-act-pair · gpt-3.5-turbo

mentions of specific individuals named Owens and aspects related to user experience (UX) design

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

anche

-0.80

 Paramount

-0.69

aghd

-0.66

 anat

-0.63

zman

-0.62

 caric

-0.61

money

-0.61

 reprim

-0.60

mand

-0.60

bath

-0.59

POSITIVE LOGITS

alez

0.86

baum

0.80

ufact

0.73

velength

0.70

ener

0.70

CRIP

0.69

chwitz

0.68

adow

0.67

ield

0.67

ibling

0.66

Activations Density 0.062%

proper nouns, particularly names such as "Owens" and terms related to user experience design (UX)

mentions of specific individuals named Owens and aspects related to user experience (UX) design

No Comments

No Known Activations