INDEX

Explanations

words that signal the beginning of an article or a piece of writing

oai_token-act-pair · gpt-3.5-turbo

instances of attribution or authorship in texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

itives

-0.82

atron

-0.71

 pains

-0.71

ioxide

-0.67

ickets

-0.65

ptions

-0.65

isable

-0.64

hement

-0.64

stones

-0.62

enthal

-0.61

POSITIVE LOGITS

akuya

0.89

 virtue

0.83

 contrast

0.79

catch

0.71

stand

0.69

pass

0.68

 implication

0.67

 Hilbert

0.66

cloneembedreportprint

0.66

JUL

0.64

Activations Density 0.025%

words that signal the beginning of an article or a piece of writing

instances of attribution or authorship in texts

No Comments

No Known Activations