INDEX

Explanations

phrases related to organizations, positions, and policies

oai_token-act-pair · gpt-3.5-turbo

references to authoritative sources and organizations

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

selection

-0.76

EXT

-0.71

 ensued

-0.70

/**

-0.69

dyl

-0.67

iques

-0.66

utations

-0.66

 solves

-0.65

 proves

-0.65

pai

-0.65

POSITIVE LOGITS

 nonpartisan

1.24

 nonprofit

1.22

 Center

1.18

 Partnership

1.15

 Association

1.06

 advocacy

1.04

 Coalition

1.03

 Federation

1.02

 Institute

1.02

 Campaign

1.01

Activations Density 0.138%

phrases related to organizations, positions, and policies

references to authoritative sources and organizations

No Comments

No Known Activations