INDEX

Explanations

references to long-term timeframes

oai_token-act-pair · gpt-3.5-turbo

references to long-term outcomes or effects

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

Reviewed

-0.81

illian

-0.78

atche

-0.78

å§«

-0.76

ropolitan

-0.74

othing

-0.73

uala

-0.72

livious

-0.71

cius

-0.71

ofer

-0.70

POSITIVE LOGITS

est

1.04

 term

0.98

liest

0.91

term

0.86

 side

0.81

iest

0.78

 aftermath

0.78

 absence

0.76

 pend

0.76

 rays

0.73

Activations Density 0.051%

references to long-term timeframes

references to long-term outcomes or effects

No Comments

No Known Activations