INDEX

Explanations

references to political figures, especially Donald Trump and associated events

oai_token-act-pair · gpt-3.5-turbo

references to Donald Trump and his associates in political contexts

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

mination

-0.75

REL

-0.69

ONY

-0.67

âĶĢ

-0.65

Contents

-0.64

ridor

-0.64

ante

-0.63

 needle

-0.63

 diagnostic

-0.63

ahi

-0.63

POSITIVE LOGITS

 pard

0.81

 Pence

0.78

 whis

0.78

 Cheney

0.77

Putin

0.74

 veto

0.70

ï

0.68

 Putin

0.67

 retweet

0.67

 impuls

0.66

Activations Density 0.379%

references to political figures, especially Donald Trump and associated events

references to Donald Trump and his associates in political contexts

No Comments

No Known Activations