INDEX

Explanations

phrases indicating significant information that should not be overlooked or forgotten

oai_token-act-pair · gpt-3.5-turbo

references to previously mentioned topics or concepts

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

imum

-0.83

rang

-0.75

terior

-0.74

rave

-0.73

sis

-0.73

adden

-0.73

twitch

-0.71

car

-0.71

hr

-0.70

unker

-0.69

POSITIVE LOGITS

 juggling

0.73

 allergies

0.71

lihood

0.70

 countless

0.66

 dozens

0.65

 innumerable

0.63

 Solitaire

0.62

 plenty

0.60

 risking

0.59

 hordes

0.58

Activations Density 0.029%

phrases indicating significant information that should not be overlooked or forgotten

references to previously mentioned topics or concepts

No Comments

No Known Activations