INDEX

Explanations

references to possession by using possessive pronouns or relationships

oai_token-act-pair · gpt-3.5-turbo

references to possessive pronouns related to individuals or groups

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

Texture

-0.79

REM

-0.78

gio

-0.76

Reviewer

-0.73

Ban

-0.73

FY

-0.72

ILE

-0.71

Serv

-0.70

AG

-0.70

POSITIVE LOGITS

own

1.39

 attendant

1.14

 surroundings

1.07

 respective

1.02

 inability

1.02

 willingness

1.01

 allies

0.99

 newfound

0.98

 ensuing

0.97

 consequ

0.97

Activations Density 0.149%

references to possession by using possessive pronouns or relationships

references to possessive pronouns related to individuals or groups

No Comments

No Known Activations