INDEX

Explanations

mentions related to violent actions or harm being inflicted

oai_token-act-pair · gpt-3.5-turbo

actions or events associated with causing harm or violence

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gers

-0.88

cius

-0.86

ger

-0.79

nings

-0.79

bard

-0.79

cean

-0.79

ese

-0.78

sell

-0.77

gered

-0.75

acea

-0.75

POSITIVE LOGITS

cipline

0.71

ngth

0.70

 Lauder

0.70

 Vict

0.70

verages

0.68

 Seym

0.67

lehem

0.67

awei

0.66

enance

0.66

INGTON

0.62

Activations Density 0.074%

mentions related to violent actions or harm being inflicted

actions or events associated with causing harm or violence

No Comments

No Known Activations