INDEX

Explanations

mentions of political figures and related activities

oai_token-act-pair · gpt-3.5-turbo

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rhy

-0.84

 intrinsic

-0.78

 structure

-0.72

gir

-0.70

 whit

-0.70

 unheard

-0.70

 timet

-0.70

 invari

-0.70

 uncontroll

-0.69

 tailor

-0.68

POSITIVE LOGITS

Calif

1.22

Ohio

1.18

Minnesota

1.18

California

1.17

Florida

1.17

Michigan

1.16

Texas

1.15

Wisconsin

1.14

Washington

1.13

Fla

1.12

Activations Density 0.027%

mentions of political figures and related activities

No Comments

No Known Activations