INDEX

Explanations

words related to political processes, such as "Cabinet," "elections," and "Senate" in the context of government activities

oai_token-act-pair · gpt-3.5-turbo

references to political decisions and positions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DRM

-0.78

 MDMA

-0.75

cig

-0.73

Maps

-0.72

 warehouses

-0.70

lag

-0.69

 MPEG

-0.68

 Customers

-0.67

 Crate

-0.66

 shoppers

-0.66

POSITIVE LOGITS

 appointing

1.58

 nomination

1.51

 appoint

1.51

 nominating

1.50

 nominate

1.48

 nominations

1.46

 appointment

1.34

 appointed

1.30

 nominees

1.29

 nominated

1.29

Activations Density 0.657%

words related to political processes, such as "Cabinet," "elections," and "Senate" in the context of government activities

references to political decisions and positions

No Comments

No Known Activations