INDEX

Explanations

phrases related to victims of various types of harm or oppression

oai_token-act-pair · gpt-3.5-turbo

references to victims of various crimes and traumatic events

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ulum

-0.77

arily

-0.71

ahead

-0.71

hua

-0.68

heads

-0.68

prints

-0.67

ortment

-0.67

shire

-0.67

agy

-0.67

liness

-0.67

POSITIVE LOGITS

 persecution

0.83

 injustice

0.83

 discrimination

0.80

 harassment

0.80

 oppression

0.78

 violence

0.78

 abuse

0.77

 gunfire

0.74

 Hurricane

0.73

 racism

0.72

Activations Density 0.085%

phrases related to victims of various types of harm or oppression

references to victims of various crimes and traumatic events

No Comments

No Known Activations