INDEX

Explanations

adversity or difficulty in various situations

oai_token-act-pair · gpt-3.5-turbo

negative expressions and phrases of disappointment

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

ourage

-0.71

rack

-0.68

 targ

-0.64

uran

-0.64

WAYS

-0.64

leans

-0.64

oing

-0.63

ujah

-0.63

regon

-0.62

lean

-0.62

POSITIVE LOGITS

partial

0.68

 Sutherland

0.66

 Pupp

0.65

 Delicious

0.64

 Penguin

0.64

 Adobe

0.63

icio

0.62

 Gregg

0.62

 Parenthood

0.60

 alas

0.60

Activations Density 0.124%

adversity or difficulty in various situations

negative expressions and phrases of disappointment

No Comments

No Known Activations