INDEX

Explanations

mentions of specific locations

oai_token-act-pair · gpt-3.5-turbo

references to locations or places indicated by the word "there."

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

CJ

-0.69

 cups

-0.59

 Milk

-0.56

Khe

-0.55

usterity

-0.55

 Armored

-0.55

 fibers

-0.55

 pound

-0.53

 Doctors

-0.53

 partial

-0.53

POSITIVE LOGITS

abouts

1.62

upon

1.12

 guiActiveUn

0.89

onian

0.86

tics

0.82

fore

0.80

with

0.79

ilitary

0.77

under

0.76

comings

0.75

Activations Density 0.093%

mentions of specific locations

references to locations or places indicated by the word "there."

No Comments

No Known Activations