INDEX

Explanations

mentions of the word "popularity"

oai_token-act-pair · gpt-3.5-turbo

references to the concept of popularity

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

erm

-0.77

alk

-0.73

 Neurolog

-0.70

rib

-0.70

uran

-0.69

 Dull

-0.67

ellig

-0.65

ibur

-0.65

 Shell

-0.64

 Matter

-0.63

POSITIVE LOGITS

ately

0.82

iqueness

0.78

itism

0.76

 popularity

0.76

popular

0.75

 ratings

0.73

ality

0.70

ability

0.69

uation

0.67

ites

0.67

Activations Density 0.025%

mentions of the word "popularity"

references to the concept of popularity

No Comments

No Known Activations