INDEX

Explanations

references to locations such as countries, cities, or regions

oai_token-act-pair · gpt-3.5-turbo

geographical names and references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

emort

-0.65

 payoff

-0.64

 stimulus

-0.59

 turnout

-0.59

enhagen

-0.57

 predictor

-0.56

 racket

-0.56

 refres

-0.53

Stand

-0.52

iseum

-0.52

POSITIVE LOGITS

tnc

0.90

sic

0.79

soDeliveryDate

0.73

tein

0.73

vous

0.72

Oss

0.69

Sty

0.65

urat

0.65

 Tale

0.64

ensis

0.64

Activations Density 1.798%

references to locations such as countries, cities, or regions

geographical names and references

No Comments

No Known Activations