INDEX

Explanations

specific entities or relationships mentioned in legal or political contexts

oai_token-act-pair · gpt-3.5-turbo

legal terminology and references to laws or regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

taboola

-0.75

ãĥĦ

-0.68

flush

-0.67

ãģ®éŃĶ

-0.67

fw

-0.66

enne

-0.65

wash

-0.62

soType

-0.58

quickShipAvailable

-0.58

ibr

-0.58

POSITIVE LOGITS

 what

0.95

how

0.74

 some

0.72

those

0.71

 those

0.70

 everything

0.67

an

0.67

 whether

0.67

0.63

what

0.62

Activations Density 0.443%

specific entities or relationships mentioned in legal or political contexts

legal terminology and references to laws or regulations

No Comments

No Known Activations