INDEX

Explanations

words related to political ideologies, specifically the term "liberal."

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "liberal."

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

pty

-0.83

Downloadha

-0.69

BuyableInstoreAndOnline

-0.68

Sharp

-0.67

ppa

-0.67

 Reincarn

-0.66

 Blazing

-0.66

agn

-0.66

BLE

-0.66

stals

-0.65

POSITIVE LOGITS

ization

1.08

 arts

1.07

izing

1.01

ized

0.95

izers

0.91

izes

0.90

 enclave

0.87

izations

0.86

izer

0.86

itarian

0.83

Activations Density 0.018%

words related to political ideologies, specifically the term "liberal."

mentions of the term "liberal."

No Comments

No Known Activations