INDEX

Explanations

phrases indicating determination and effort towards accomplishing a task or goal

oai_token-act-pair · gpt-3.5-turbo

phrases indicating capabilities and actions of individuals

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

hower

-0.71

 Lauder

-0.67

pora

-0.67

ENCY

-0.65

geries

-0.63

 Survivors

-0.62

utherford

-0.62

cture

-0.60

 Examination

-0.60

 Shap

-0.59

POSITIVE LOGITS

 legally

0.82

 reasonably

0.82

 lawfully

0.78

 normally

0.75

 advertised

0.71

usual

0.69

itaire

0.68

iest

0.65

 responsibly

0.64

 deserve

0.64

Activations Density 0.097%

phrases indicating determination and effort towards accomplishing a task or goal

phrases indicating capabilities and actions of individuals

No Comments

No Known Activations