INDEX

Explanations

phrases indicating certainty or confidence

oai_token-act-pair · gpt-3.5-turbo

phrases indicating certainty or inevitability

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ufact

-0.77

vernment

-0.75

edia

-0.66

intosh

-0.64

gdala

-0.63

annis

-0.61

INT

-0.59

olid

-0.58

asus

-0.58

akespeare

-0.57

POSITIVE LOGITS

ties

1.13

fire

0.98

footed

0.95

ty

0.94

sk

0.89

faced

0.86

stre

0.73

stall

0.72

blade

0.71

ples

0.71

Activations Density 0.032%

phrases indicating certainty or confidence

phrases indicating certainty or inevitability

No Comments

No Known Activations