INDEX

Explanations

references to specific political parties and individuals

oai_token-act-pair · gpt-3.5-turbo

mentions of political parties and their officials

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

aturation

-0.83

sis

-0.80

ĸļ

-0.79

 Bezos

-0.77

iceps

-0.71

atur

-0.68

ous

-0.67

ulous

-0.67

orer

-0.67

orage

-0.66

POSITIVE LOGITS

 Gael

1.05

 Ministers

0.95

 parliament

0.92

 councillors

0.90

MPs

0.89

 Confederation

0.88

 Commissioners

0.87

 ministerial

0.87

 Parliamentary

0.85

 Examiner

0.85

Activations Density 0.084%

references to specific political parties and individuals

mentions of political parties and their officials

No Comments

No Known Activations