INDEX

Explanations

names of political figures and related terms

oai_token-act-pair · gpt-3.5-turbo

references to Donald Trump and related entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 analyse

-0.71

âĶĢâĶĢ

-0.70

 realise

-0.67

 Mages

-0.66

 decomp

-0.65

ptin

-0.65

 analys

-0.65

 realised

-0.64

 explorers

-0.64

 labou

-0.64

POSITIVE LOGITS

Republicans

1.00

Republican

1.00

 Republican

0.99

 Politico

0.96

GOP

0.96

GOP

0.96

Hillary

0.95

Democrats

0.94

Senate

0.92

Trump

0.92

Activations Density 4.088%

names of political figures and related terms

references to Donald Trump and related entities

No Comments

No Known Activations