INDEX

Explanations

incidents involving death and destruction

oai_token-act-pair · gpt-3.5-turbo

phrases related to violent events and casualties

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

abase

-0.76

 Marketable

-0.71

 Invention

-0.67

wcsstore

-0.64

 vanity

-0.63

 Framework

-0.61

TPP

-0.60

heit

-0.60

Ide

-0.60

minecraft

-0.59

POSITIVE LOGITS

 injuring

0.86

 bystanders

0.81

 evac

0.78

rench

0.76

 gunmen

0.75

 casualties

0.75

ousands

0.73

 victims

0.72

 inflamm

0.72

 wounding

0.72

Activations Density 0.182%

incidents involving death and destruction

phrases related to violent events and casualties

No Comments

No Known Activations