INDEX

Explanations

names of political figures and governmental entities

oai_token-act-pair · gpt-3.5-turbo

references to political leaders and significant geopolitical events

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

DragonMagazine

-0.84

anian

-0.82

"}],"

-0.67

.","

-0.64

å°Ĩ

-0.64

bral

-0.63

"}

-0.62

partisan

-0.62

gru

-0.60

andom

-0.60

POSITIVE LOGITS

JFK

0.66

TBA

0.65

La

0.65

 Chick

0.64

Cla

0.64

Dak

0.61

 Olymp

0.61

Cad

0.61

 Uran

0.61

Et

0.60

Activations Density 0.800%

names of political figures and governmental entities

references to political leaders and significant geopolitical events

No Comments

No Known Activations