INDEX

Explanations

proper nouns related to people

oai_token-act-pair · gpt-3.5-turbo

names or terms associated with specific individuals or entities

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

 feder

-0.80

 ACTIONS

-0.73

é¾įå

-0.70

pse

-0.64

UTERS

-0.64

akeru

-0.60

AUD

-0.59

ĨĴ

-0.59

 Helpful

-0.59

theless

-0.58

POSITIVE LOGITS

aten

0.78

iman

0.74

edi

0.73

nen

0.70

azi

0.67

ati

0.66

olean

0.65

puff

0.65

angs

0.64

har

0.64

Activations Density 0.281%

proper nouns related to people

names or terms associated with specific individuals or entities

No Comments

No Known Activations