INDEX

Explanations

proper nouns related to names or locations

oai_token-act-pair · gpt-3.5-turbo

names of locations and people associated with them

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

pread

-0.86

mers

-0.83

vg

-0.79

tips

-0.78

annah

-0.75

parent

-0.75

ames

-0.75

eker

-0.73

oran

-0.72

Redd

-0.71

POSITIVE LOGITS

 Cutler

0.78

 appraisal

0.78

 chop

0.66

inez

0.65

 leveled

0.65

 Burnett

0.63

 Fiorina

0.62

inois

0.62

 Comedy

0.61

 appra

0.61

Activations Density 0.025%

proper nouns related to names or locations

names of locations and people associated with them

No Comments

No Known Activations