INDEX

Explanations

references to kits or components within a particular context like car modifications or hobby-related activities

oai_token-act-pair · gpt-3.5-turbo

references to various types of kits

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

arching

-0.91

ews

-0.72

 Democr

-0.71

south

-0.68

acebook

-0.67

encer

-0.66

ä¼

-0.66

unct

-0.64

vantage

-0.62

quished

-0.62

POSITIVE LOGITS

chens

1.28

kit

1.03

kit

1.02

 kits

0.99

kat

0.96

Kit

0.85

chy

0.82

Kat

0.78

 Kats

0.78

 Kits

0.73

Activations Density 0.012%

references to kits or components within a particular context like car modifications or hobby-related activities

references to various types of kits

No Comments

No Known Activations