INDEX

Explanations

mentions of political entities and related terms, particularly focusing on references to the Kremlin

oai_token-act-pair · gpt-3.5-turbo

references to the Kremlin and its associated entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

âĢ¢âĢ¢âĢ¢âĢ¢

-0.77

adoes

-0.74

ICAN

-0.73

ORGE

-0.73

ayer

-0.72

bee

-0.70

inals

-0.70

aith

-0.67

 Starr

-0.66

terson

-0.65

POSITIVE LOGITS

 Kremlin

0.97

 Moscow

0.92

kaya

0.90

 Dmitry

0.90

 rall

0.86

sky

0.85

 Dmit

0.85

ski

0.80

achev

0.80

rolet

0.80

Activations Density 0.055%

mentions of political entities and related terms, particularly focusing on references to the Kremlin

references to the Kremlin and its associated entities

No Comments

No Known Activations