INDEX

Explanations

dates or time periods

oai_token-act-pair · gpt-3.5-turbo

references to time periods and specific dates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

Reviewed

-0.70

Reviewer

-0.68

Lex

-0.68

Ax

-0.64

Values

-0.61

ographed

-0.60

 Genius

-0.58

Shot

-0.58

Ball

-0.58

Offline

-0.57

POSITIVE LOGITS

 onwards

0.85

angering

0.75

uberty

0.75

 onward

0.73

oulos

0.70

spection

0.69

iannopoulos

0.69

opers

0.69

uates

0.67

 registrations

0.67

Activations Density 0.263%

dates or time periods

references to time periods and specific dates

No Comments

No Known Activations