INDEX

Explanations

phrases related to legal terms and regulations

oai_token-act-pair · gpt-3.5-turbo

terms related to regulations, policies, and formal agreements

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

pieces

-0.74

fights

-0.73

rams

-0.73

 hell

-0.72

fed

-0.71

 chains

-0.69

 queen

-0.69

 shine

-0.69

ching

-0.69

rows

-0.68

POSITIVE LOGITS

 Development

1.31

 Affairs

1.26

 Assessment

1.24

 Services

1.23

 Identification

1.23

 Assistance

1.20

 Association

1.20

 Relations

1.19

 Investigations

1.19

 Computing

1.18

Activations Density 0.227%

phrases related to legal terms and regulations

terms related to regulations, policies, and formal agreements

No Comments

No Known Activations