INDEX

Explanations

adjective-noun pairs indicating satisfaction or acceptance

oai_token-act-pair · gpt-3.5-turbo

variations of the word "content."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

rolet

-0.71

 damn

-0.63

Äĩ

-0.61

 Siem

-0.60

udeb

-0.59

DAM

-0.59

ipers

-0.59

iami

-0.59

Dee

-0.58

JD

-0.57

POSITIVE LOGITS

edly

1.44

ment

1.06

ioned

0.99

ions

0.91

iar

0.85

 content

0.82

icut

0.81

onite

0.80

Content

0.80

ication

0.79

Activations Density 0.020%

adjective-noun pairs indicating satisfaction or acceptance

variations of the word "content."

No Comments

No Known Activations