INDEX

Explanations

words related to violence and hate crimes

oai_token-act-pair · gpt-3.5-turbo

references to violence and hate crimes

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

shire

-0.88

sonian

-0.79

gio

-0.74

 Parables

-0.73

phrine

-0.70

hower

-0.70

 Oops

-0.69

 Guinness

-0.68

ROM

-0.68

 Lunar

-0.67

POSITIVE LOGITS

 intimidation

0.98

 violence

0.98

 retaliation

0.94

 indiscrim

0.93

 perpetrated

0.93

 harassment

0.93

 harass

0.92

 retribution

0.89

 persecution

0.89

 slurs

0.85

Activations Density 0.357%

words related to violence and hate crimes

references to violence and hate crimes

No Comments

No Known Activations