INDEX

Explanations

phrases related to physical abilities, particularly speed, agility, athleticism, and work ethic

oai_token-act-pair · gpt-3.5-turbo

terms related to athletic performance and skills

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ciation

-0.76

Ń·

-0.74

Recommend

-0.70

 Term

-0.69

Kids

-0.68

ļéĨĴ

-0.68

ģĸ

-0.66

ĨĴ

-0.66

EMS

-0.65

 Schools

-0.65

POSITIVE LOGITS

 charisma

1.13

 physique

0.97

 agility

0.93

istry

0.93

 knack

0.91

 hust

0.82

 athleticism

0.81

 deft

0.81

 athlet

0.81

 impecc

0.80

Activations Density 0.290%

phrases related to physical abilities, particularly speed, agility, athleticism, and work ethic

terms related to athletic performance and skills

No Comments

No Known Activations