INDEX

Explanations

statistical data related phrases

oai_token-act-pair · gpt-3.5-turbo

numerical data related to statistics or counts

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

DragonMagazine

-0.76

usterity

-0.71

 Parables

-0.69

learning

-0.66

 Understanding

-0.66

Understanding

-0.65

Learning

-0.63

RAW

-0.62

leans

-0.61

 rant

-0.60

POSITIVE LOGITS

 outright

0.92

 apiece

0.91

 consecut

0.82

 total

0.77

eligible

0.74

 rated

0.71

 respondents

0.66

ister

0.66

 classified

0.65

 individually

0.65

Activations Density 0.281%

statistical data related phrases

numerical data related to statistics or counts

No Comments

No Known Activations