INDEX

Explanations

phrases related to providing information to the public

oai_token-act-pair · gpt-3.5-turbo

references to the public 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Reloaded

-0.71

 Deadly

-0.69

Scroll

-0.68

Pg

-0.68

RANT

-0.67

scrib

-0.66

Sax

-0.65

imov

-0.65

Prev

-0.63

BuyableInstoreAndOnline

-0.62

POSITIVE LOGITS

 outcry

0.88

 purse

0.87

 broadcaster

0.80

izes

0.80

eye

0.79

ised

0.74

 servants

0.74

 perception

0.74

 treasury

0.72

 sphere

0.71

Activations Density 0.039%

phrases related to providing information to the public

references to the public in various contexts

No Comments

No Known Activations