INDEX

Explanations

mentions of individuals being a part of a group or organization

oai_token-act-pair · gpt-3.5-turbo

references to membership in organizations or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

bows

-0.70

arp

-0.67

ILLE

-0.66

 mete

-0.65

condition

-0.65

 freezing

-0.64

©¶æ

-0.64

BUS

-0.64

aber

-0.63

hur

-0.62

POSITIVE LOGITS

 member

0.96

holder

0.91

hips

0.85

 Member

0.84

holders

0.84

ertodd

0.82

member

0.82

uary

0.82

ularity

0.79

nered

0.78

Activations Density 0.021%

mentions of individuals being a part of a group or organization

references to membership in organizations or groups

No Comments

No Known Activations