INDEX

Explanations

mentions of the word "turkey."

oai_token-act-pair · gpt-3.5-turbo

references to turkey

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ardo

-0.79

iott

-0.75

iam

-0.74

ingly

-0.72

 largeDownload

-0.70

ister

-0.69

ances

-0.68

orius

-0.68

esis

-0.66

inel

-0.66

POSITIVE LOGITS

geon

0.80

geons

0.80

gie

0.75

STEM

0.74

Rex

0.72

 Sabres

0.71

gery

0.69

BIL

0.69

Nug

0.65

pora

0.64

Activations Density 0.029%

mentions of the word "turkey."

references to turkey

No Comments

No Known Activations