INDEX

Explanations

questions or uncertainties expressed using punctuation symbols

oai_token-act-pair · gpt-3.5-turbo

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

utic

-0.68

 Dickinson

-0.67

zona

-0.67

uan

-0.67

oids

-0.66

asta

-0.66

 Brach

-0.66

inki

-0.65

aceous

-0.65

hement

-0.63

POSITIVE LOGITS

Ħ¢

0.80

ĸļ

0.78

 Laure

0.70

important

0.67

really

0.62

?:

0.62

actual

0.62

utm

0.60

.?

0.60

iry

0.60

Activations Density 0.022%

questions or uncertainties expressed using punctuation symbols

No Comments

No Known Activations