INDEX

Explanations

terms related to media, such as Media Query, Media Lab, Media Standards, and Media Network

oai_token-act-pair · gpt-3.5-turbo

references to media-related entities or organizations

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

owsky

-0.74

ranch

-0.71

bats

-0.69

-0.65

 Salvador

-0.65

nob

-0.65

cker

-0.65

ģ«

-0.63

uca

-0.63

ohl

-0.62

POSITIVE LOGITS

eval

1.32

 outlets

0.93

wiki

0.90

 literacy

0.82

 playback

0.80

mog

0.78

 blackout

0.76

 Matters

0.75

 consolidation

0.74

 outlet

0.74

Activations Density 0.029%

terms related to media, such as Media Query, Media Lab, Media Standards, and Media Network

references to media-related entities or organizations

No Comments

No Known Activations