INDEX

Explanations

mentions of specific or emphasized items or concepts within a context

oai_token-act-pair · gpt-3.5-turbo

references to specific topics or entities

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

lyn

-0.76

unts

-0.74

IR

-0.69

board

-0.69

UD

-0.66

USD

-0.66

NI

-0.65

li

-0.64

bane

-0.64

POSITIVE LOGITS

ties

0.94

ities

0.89

 embodiments

0.82

iates

0.81

styles

0.80

 batches

0.77

izations

0.77

wcs

0.77

 identifiable

0.76

isations

0.76

Activations Density 0.014%

mentions of specific or emphasized items or concepts within a context

references to specific topics or entities

No Comments

No Known Activations