INDEX

Explanations

names of people or locations

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names of individuals and locations

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

Downloadha

-0.75

 Frozen

-0.68

ndra

-0.67

warm

-0.64

 favour

-0.63

tics

-0.62

adesh

-0.62

 Guilty

-0.61

 polar

-0.59

daily

-0.58

POSITIVE LOGITS

ONSORED

0.83

Department

0.67

ENSE

0.66

itzer

0.65

utenberg

0.65

ourke

0.63

ãĤ¼ãĤ¦ãĤ¹

0.63

agall

0.59

 Dept

0.59

nel

0.58

Activations Density 0.309%

names of people or locations

proper nouns, specifically names of individuals and locations

No Comments

No Known Activations