INDEX

Explanations

words and phrases indicating positive characteristics or aspects

oai_token-act-pair · gpt-3.5-turbo

descriptive adjectives that highlight positive attributes and significance

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

ĸļ

-0.97

anwhile

-0.93

externalActionCode

-0.82

ensibly

-0.81

ordon

-0.81

ully

-0.78

©¶æ

-0.78

ldom

-0.77

anship

-0.77

deen

-0.76

POSITIVE LOGITS

 examples

1.06

 contenders

1.02

 moments

0.97

 things

0.96

 names

0.93

 surprises

0.91

 instances

0.91

 items

0.91

 paragraphs

0.90

 ideas

0.89

Activations Density 0.330%

words and phrases indicating positive characteristics or aspects

descriptive adjectives that highlight positive attributes and significance

No Comments

No Known Activations