INDEX

Explanations

mentions of the word "Kremlin" in the text

oai_token-act-pair · gpt-3.5-turbo

mentions of the Kremlin and related political contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Thom

-0.85

ORGE

-0.79

 Kear

-0.77

 Scotch

-0.72

Thompson

-0.70

matter

-0.70

Haw

-0.69

IGN

-0.69

ients

-0.69

Redd

-0.68

POSITIVE LOGITS

 Kremlin

1.03

 rall

0.94

 dictatorship

0.93

achev

0.86

 dictator

0.85

kaya

0.82

aganda

0.81

 Jinping

0.80

 disinformation

0.79

 meddling

0.74

Activations Density 0.005%

mentions of the word "Kremlin" in the text

mentions of the Kremlin and related political contexts

No Comments

No Known Activations