INDEX

Explanations

links or recommendations to read or explore something further

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "so" in various contexts

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

keepers

-0.78

ctrl

-0.75

keeper

-0.69

uine

-0.67

 wrench

-0.63

keeping

-0.63

bern

-0.62

 decency

-0.61

 rusty

-0.61

atur

-0.60

POSITIVE LOGITS

 COVER

1.06

 READ

0.99

GROUND

0.98

LINE

0.95

 Featured

0.92

ILE

0.88

FTWARE

0.87

LIST

0.86

ODUCT

0.86

LY

0.86

Activations Density 0.026%

links or recommendations to read or explore something further

occurrences of the word "so" in various contexts

No Comments

No Known Activations