INDEX

Explanations

terms related to specific organizations or locations with high activation values

oai_token-act-pair · gpt-3.5-turbo

references to specific locations, organizations, or notable subjects

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

Negative Logits

ived

-0.59

Bod

-0.53

rb

-0.52

ãģ¯

-0.51

idth

-0.50

rss

-0.50

 Brit

-0.50

nos

-0.49

raw

-0.48

Ô

-0.48

POSITIVE LOGITS

rul

0.61

 phenotype

0.57

 holdings

0.54

 itself

0.54

 herself

0.51

 Citadel

0.50

 apparatus

0.49

 himself

0.48

 shenan

0.48

agine

0.47

Activations Density 1.117%

terms related to specific organizations or locations with high activation values

references to specific locations, organizations, or notable subjects

No Known Activations