INDEX

Explanations

names, titles, and positions of people and officials

oai_token-act-pair · gpt-3.5-turbo

terms related to political figures and their titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

isSpecialOrderable

-0.73

Cub

-0.73

landish

-0.63

ILLE

-0.62

 cliff

-0.62

TIME

-0.61

 checkout

-0.61

Ohio

-0.61

bucks

-0.60

employment

-0.60

POSITIVE LOGITS

 Rahul

1.45

Vij

1.44

 Vish

1.41

 Krishna

1.40

 Shiv

1.40

Muk

1.39

 Kumar

1.35

 Amit

1.34

 Chand

1.32

 Chandra

1.32

Activations Density 0.174%

names, titles, and positions of people and officials

terms related to political figures and their titles

No Comments

No Known Activations