INDEX

Explanations

phrases related to top-tier quality or excellence

oai_token-act-pair · gpt-3.5-turbo

references to classifications or rankings of individuals or entities

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

YA

-0.81

agen

-0.79

HUD

-0.78

SN

-0.77

pty

-0.74

Party

-0.73

WAR

-0.71

alone

-0.69

ocene

-0.69

Shares

-0.69

POSITIVE LOGITS

 performers

0.98

 talents

0.91

 talent

0.90

 performer

0.87

 entertain

0.85

 sized

0.82

smanship

0.81

 athletic

0.79

 hospitality

0.78

 professionalism

0.77

Activations Density 0.089%

phrases related to top-tier quality or excellence

references to classifications or rankings of individuals or entities

No Comments

No Known Activations