INDEX

Explanations

mentions of political figures or entities

oai_token-act-pair · gpt-3.5-turbo

repeated references to a specific individual, particularly in a political context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 mathemat

-0.82

 fortun

-0.79

 Jericho

-0.75

Yor

-0.72

 Franch

-0.69

 interf

-0.68

cob

-0.67

 Brist

-0.67

Tid

-0.67

 airs

-0.65

POSITIVE LOGITS

Ļ

1.53

¬

1.46

ı

1.29

Ħ¢

1.28

ħ

1.23

ĳ

1.23

¡

1.20

Ĵ

1.20

Ķ

1.19

¤

1.19

Activations Density 0.256%

mentions of political figures or entities

repeated references to a specific individual, particularly in a political context

No Comments

No Known Activations