INDEX

Explanations

references to originality or original content

oai_token-act-pair · gpt-3.5-turbo

references to original content or originality in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ucket

-0.72

 Simulator

-0.70

wal

-0.69

ega

-0.67

roph

-0.66

rom

-0.66

angs

-0.65

rolet

-0.65

walk

-0.64

ower

-0.63

POSITIVE LOGITS

ity

1.41

ITY

1.10

izations

0.95

ities

0.86

itÃ©

0.85

lly

0.85

itiz

0.82

itized

0.81

iator

0.80

smanship

0.79

Activations Density 0.020%

references to originality or original content

references to original content or originality in various contexts

No Comments

No Known Activations