INDEX

Explanations

mentions of political figures, particularly former presidents and vice presidents

oai_token-act-pair · gpt-3.5-turbo

references to political figures and their titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Sensor

-0.68

atum

-0.64

eta

-0.63

 radius

-0.63

âĹ¼

-0.63

fw

-0.62

endi

-0.62

Tree

-0.62

Limited

-0.60

 issu

-0.60

POSITIVE LOGITS

 Yugoslavia

0.89

 Saddam

0.88

 Colin

0.79

 Lyndon

0.79

turned

0.78

 Watergate

0.77

 Newt

0.77

 Abel

0.77

 disgr

0.75

 Yugoslav

0.75

Activations Density 0.175%

mentions of political figures, particularly former presidents and vice presidents

references to political figures and their titles

No Comments

No Known Activations