INDEX

Explanations

details related to violent incidents involving shooting and killing

oai_token-act-pair · gpt-3.5-turbo

phrases related to shootings and killings

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ional

-0.84

Trade

-0.80

heit

-0.79

 Administ

-0.75

JV

-0.75

ahime

-0.72

ç«

-0.72

isd

-0.72

Reviewer

-0.72

soType

-0.70

POSITIVE LOGITS

 unarmed

0.93

 Shotgun

0.92

 espresso

0.89

 bullets

0.83

ovie

0.81

 shotgun

0.81

 guns

0.77

 gunfire

0.77

 kill

0.76

 pellets

0.74

Activations Density 0.174%

details related to violent incidents involving shooting and killing

phrases related to shootings and killings

No Comments

No Known Activations