INDEX

Explanations

phrases related to following guidelines or procedures

oai_token-act-pair · gpt-3.5-turbo

references to guidelines or rules

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

wcs

-0.82

votes

-0.76

raise

-0.75

ricular

-0.75

omorph

-0.74

uph

-0.71

overe

-0.69

destruct

-0.68

 decrypt

-0.66

 coerc

-0.66

POSITIVE LOGITS

Tik

0.67

 ranch

0.66

 Woods

0.65

ERA

0.62

Kau

0.62

 Ranch

0.62

 Anaheim

0.62

 Anderson

0.61

ILLE

0.61

 royalty

0.61

Activations Density 0.000%

phrases related to following guidelines or procedures

references to guidelines or rules

No Comments

No Known Activations