INDEX

Explanations

stories or scenarios involving theft or criminal activities

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

quickShipAvailable

-0.70

Contribut

-0.69

kowski

-0.69

involved

-0.69

rition

-0.68

etheless

-0.68

 GOODMAN

-0.67

rored

-0.67

displayText

-0.66

ï¸ı

-0.65

POSITIVE LOGITS

 naughty

0.89

 mysterious

0.82

 chores

0.80

 magically

0.75

 inventions

0.74

 imaginary

0.74

 strange

0.74

 gossip

0.73

 worthless

0.73

 pornographic

0.73

Activations Density 1.044%

stories or scenarios involving theft or criminal activities

No Comments

No Known Activations