INDEX

Explanations

phrases related to identifying and addressing various needs

oai_token-act-pair · gpt-3.5-turbo

references to various types of needs in different contexts

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

é¾

-0.80

âĸ¬

-0.66

Bom

-0.65

onym

-0.62

thumbnails

-0.62

vind

-0.62

 rabbit

-0.61

smoking

-0.60

uclear

-0.59

alty

-0.59

POSITIVE LOGITS

lessly

0.83

cale

0.83

giving

0.74

afety

0.73

afe

0.73

igslist

0.70

 dictate

0.68

ucker

0.66

 constrained

0.65

pace

0.64

Activations Density 0.042%

phrases related to identifying and addressing various needs

references to various types of needs in different contexts

No Comments

No Known Activations