INDEX

Explanations

phrases related to directions or instructions

oai_token-act-pair · gpt-3.5-turbo

common pronouns and their associated verbs in context

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

 rush

-0.65

inav

-0.62

 ensu

-0.60

"}],"

-0.57

\":

-0.56

Preview

-0.56

 Danish

-0.56

 Lobby

-0.55

 Scand

-0.55

Adv

-0.55

POSITIVE LOGITS

mere

0.93

 merely

0.92

ifle

0.80

Instead

0.79

ngth

0.77

 simply

0.75

Berry

0.75

Nor

0.74

erville

0.71

gemony

0.71

Activations Density 0.530%

phrases related to directions or instructions

common pronouns and their associated verbs in context

No Comments

No Known Activations