INDEX

Explanations

different kinds or types of items or categories within a set

oai_token-act-pair · gpt-3.5-turbo

references to categories and classifications

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

NING

-0.71

Blade

-0.70

PDATE

-0.68

 Tycoon

-0.67

IRO

-0.67

ITED

-0.67

WN

-0.65

ior

-0.63

interstitial

-0.63

 Thumbnails

-0.63

POSITIVE LOGITS

etting

1.39

etter

1.02

pace

0.99

paces

0.99

hots

0.80

hell

0.79

afe

0.78

of

0.76

uit

0.75

cale

0.75

Activations Density 0.039%

different kinds or types of items or categories within a set

references to categories and classifications

No Comments

No Known Activations