INDEX

Explanations

phrases related to incidents or events involving violence or law enforcement

oai_token-act-pair · gpt-3.5-turbo

instances of violent incidents and related injuries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 persuasion

-0.99

 persu

-0.95

 favour

-0.93

 shrinking

-0.92

 innov

-0.89

 tempt

-0.88

 enriched

-0.87

 mastering

-0.86

 tink

-0.85

 striving

-0.85

POSITIVE LOGITS

Investigators

1.91

Authorities

1.85

Police

1.83

Officers

1.71

Officials

1.67

According

1.67

Detect

1.61

Prosecutors

1.58

Sources

1.55

Anyone

1.54

Activations Density 0.282%

phrases related to incidents or events involving violence or law enforcement

instances of violent incidents and related injuries

No Comments

No Known Activations