INDEX

Explanations

legal terms and procedures

oai_token-act-pair · gpt-3.5-turbo

legal terminology and specific classifications

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

AND

-0.62

 TODAY

-0.62

 Aval

-0.60

HAS

-0.56

and

-0.54

hematically

-0.54

 Kimmel

-0.53

 today

-0.51

ËĪ

-0.49

"]=>

-0.49

POSITIVE LOGITS

 alike

1.57

 respectively

1.57

 versa

0.94

 thereof

0.91

depending

0.90

rosso

0.72

emale

0.71

SPONSORED

0.67

 modes

0.66

 architectures

0.66

Activations Density 0.692%

legal terms and procedures

legal terminology and specific classifications

No Comments

No Known Activations