INDEX

Explanations

phrases related to acts of violence

oai_token-act-pair · gpt-3.5-turbo

references to individuals involved in an incident or event

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Optim

-0.74

 largeDownload

-0.70

âĺħâĺħ

-0.69

âĺħ

-0.69

htaking

-0.67

uits

-0.67

eworthy

-0.65

 Worlds

-0.64

earch

-0.63

 Wilderness

-0.63

POSITIVE LOGITS

'd

1.00

 pleaded

0.87

 drove

0.87

 complained

0.87

'll

0.87

 boarded

0.86

 swore

0.83

 underwent

0.82

 awoke

0.82

 testified

0.82

Activations Density 0.252%

phrases related to acts of violence

references to individuals involved in an incident or event

No Comments

No Known Activations