INDEX

Explanations

mentions of political figures, especially presidents

oai_token-act-pair · gpt-3.5-turbo

mentions of "President" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

anca

-0.66

MpServer

-0.62

TOR

-0.59

essen

-0.59

lighting

-0.59

 caster

-0.59

âĵĺ

-0.59

 chrom

-0.58

yrinth

-0.58

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

-0.57

POSITIVE LOGITS

 Barack

1.52

 Obama

1.40

 Donald

1.24

 Recep

1.14

 Trump

1.13

 Bashar

1.09

 Lyndon

1.04

 Rodrigo

1.00

 Ronald

0.98

 George

0.98

Activations Density 0.060%

mentions of political figures, especially presidents

mentions of "President" in various contexts

No Comments

No Known Activations