INDEX

Explanations

mentions of smoking or smokers

oai_token-act-pair · gpt-3.5-turbo

terms related to smoking or smokers

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

quartered

-0.88

artz

-0.87

blem

-0.83

ailable

-0.81

quished

-0.79

lisher

-0.78

usha

-0.78

inventoryQuantity

-0.75

digy

-0.73

 defe

-0.73

POSITIVE LOGITS

 Robots

0.71

 Guys

0.70

 Sounds

0.70

Gus

0.70

 Married

0.69

 Bugs

0.69

 There

0.69

 Maybe

0.69

 Unfortunately

0.69

 Perhaps

0.68

Activations Density 0.000%

mentions of smoking or smokers

terms related to smoking or smokers

No Comments

No Known Activations