INDEX

Explanations

legal and courtroom-related terms

oai_token-act-pair · gpt-3.5-turbo

legal terminology and references to accountability and roles 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 @ 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

agog

-0.55

 simulac

-0.54

 mish

-0.53

mil

-0.53

INFO

-0.50

eret

-0.49

ain

-0.48

 burgl

-0.47

pired

-0.47

 Freak

-0.47

POSITIVE LOGITS

 because

0.80

 altogether

0.76

 lest

0.76

 whilst

0.73

 unless

0.73

 anymore

0.71

 rather

0.66

 amid

0.65

 although

0.65

due

0.64

Activations Density 1.345%

legal and courtroom-related terms

legal terminology and references to accountability and roles in various contexts

No Comments

No Known Activations