INDEX

Explanations

terms related to proposing or suggesting ideas for specific situations or scenarios

oai_token-act-pair · gpt-3.5-turbo

phrases related to suggested solutions or ideas for improvement

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

hest

-0.78

imum

-0.73

Critical

-0.68

perfect

-0.67

 Failed

-0.66

 cannot

-0.65

 rightly

-0.65

Ñı

-0.64

 rightfully

-0.62

POSITIVE LOGITS

 somew

0.87

 someday

0.86

 recons

0.76

 arrang

0.74

 glim

0.71

 monop

0.70

 reintrodu

0.70

 analogous

0.70

instead

0.69

 corrid

0.69

Activations Density 0.794%

terms related to proposing or suggesting ideas for specific situations or scenarios

phrases related to suggested solutions or ideas for improvement

No Comments

No Known Activations