INDEX

Explanations

phrases asking for clarification or explanation

oai_token-act-pair · gpt-3.5-turbo

questions or statements expressing uncertainty

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

ulic

-0.78

enberg

-0.72

robe

-0.69

ubs

-0.69

gi

-0.66

ped

-0.66

enburg

-0.66

por

-0.65

hon

-0.63

eer

-0.62

POSITIVE LOGITS

 happened

1.32

 happens

1.30

soever

1.25

 transpired

1.16

 kinds

1.15

 constitutes

1.12

 happ

1.07

 else

1.06

 sorts

1.04

 distinguishes

0.97

Activations Density 0.100%

phrases asking for clarification or explanation

questions or statements expressing uncertainty

No Comments

No Known Activations