INDEX

Explanations

words related to specific identifiers or labels

oai_token-act-pair · gpt-3.5-turbo

instances of the term "id" in various formats or 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

wcs

-0.75

idon

-0.64

Thumbnail

-0.63

ħĭ

-0.63

orial

-0.61

wagen

-0.60

Ago

-0.59

olicy

-0.59

beans

-0.58

 Galile

-0.58

POSITIVE LOGITS

REDACTED

0.85

DX

0.70

Ö¼

0.70

 Akin

0.65

utive

0.65

ablishment

0.62

iru

0.60

una

0.60

ANCE

0.59

Bir

0.59

Activations Density 0.152%

words related to specific identifiers or labels

instances of the term "id" in various formats or contexts

No Comments

No Known Activations