INDEX

Explanations

terms related to leadership and management

oai_token-act-pair · gpt-3.5-turbo

references to leadership

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Gund

-0.79

enegger

-0.78

isher

-0.78

 Neighbor

-0.73

nee

-0.72

 Coulter

-0.71

agon

-0.70

fff

-0.70

 Dull

-0.69

ighth

-0.66

POSITIVE LOGITS

ership

1.06

ahime

0.94

 leadership

0.92

leaders

0.85

doms

0.79

wcs

0.78

 aspirations

0.77

 ambitions

0.76

 contender

0.74

 aspir

0.73

Activations Density 0.025%

terms related to leadership and management

references to leadership

No Comments

No Known Activations