INDEX

Explanations

mentions of political seats

oai_token-act-pair · gpt-3.5-turbo

references to political positions or electoral seats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

-0.76

 Turtles

-0.75

ocrine

-0.71

 Entertainment

-0.69

sonian

-0.69

STD

-0.67

onut

-0.65

ODUCT

-0.64

obyl

-0.64

icol

-0.64

POSITIVE LOGITS

holders

1.14

holder

1.13

seat

1.04

belt

0.98

 seat

0.95

mate

0.93

 vacated

0.92

vote

0.91

 holders

0.91

mates

0.90

Activations Density 0.016%

mentions of political seats

references to political positions or electoral seats

No Comments

No Known Activations