INDEX

Explanations

phrases related to thoughts, expectations, and imaginations

oai_token-act-pair · gpt-3.5-turbo

phrases indicating assumptions or common perceptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Miko

-0.65

 âĹı

-0.64

 Pruitt

-0.64

 Phelps

-0.60

WWF

-0.60

ritz

-0.59

 mediation

-0.59

 disarm

-0.57

 Katy

-0.57

 Central

-0.56

POSITIVE LOGITS

Downloadha

0.84

ault

0.75

iar

0.72

eeds

0.71

heit

0.69

uma

0.67

um

0.66

 charism

0.65

 otherwise

0.64

 charact

0.63

Activations Density 0.185%

phrases related to thoughts, expectations, and imaginations

phrases indicating assumptions or common perceptions

No Comments

No Known Activations