INDEX

Explanations

mentions of political figures, specifically presidents

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "President"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 grind

-0.69

 scrape

-0.66

esc

-0.64

QC

-0.63

Gy

-0.62

 secondary

-0.62

 eyeb

-0.62

Ib

-0.62

 litter

-0.62

 shift

-0.60

POSITIVE LOGITS

President

3.62

president

2.53

 President

2.23

Secretary

2.05

 PRESIDENT

2.04

 Presidents

1.91

Obama

1.80

 president

1.79

Vice

1.76

Senator

1.74

Activations Density 0.013%

mentions of political figures, specifically presidents

mentions of the word "President"

No Comments

No Known Activations