INDEX

Explanations

explanatory phrases or sentences

oai_token-act-pair · gpt-3.5-turbo

instances of the word "explained" and its variations, indicating explanations or clarifications being made

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

illet

-0.74

jet

-0.72

cess

-0.72

etooth

-0.72

estial

-0.70

externalActionCode

-0.68

inal

-0.68

ascus

-0.68

Pont

-0.68

naissance

-0.66

POSITIVE LOGITS

why

1.04

WHY

0.94

how

0.80

 Languages

0.74

 succinct

0.73

why

0.72

 concise

0.71

udic

0.70

WER

0.69

ĸļ

0.68

Activations Density 0.025%

explanatory phrases or sentences

instances of the word "explained" and its variations, indicating explanations or clarifications being made

No Comments

No Known Activations