INDEX

Explanations

pronouns indicating possession or belonging

oai_token-act-pair · gpt-3.5-turbo

possessive pronouns and related restrictions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 largeDownload

-0.71

 UNHCR

-0.70

shaw

-0.69

noon

-0.68

Tang

-0.65

dding

-0.63

 Moody

-0.63

UNCH

-0.63

shed

-0.63

tar

-0.61

POSITIVE LOGITS

own

1.55

 entire

1.22

selves

0.97

 respective

0.94

 cherished

0.93

 preferred

0.92

 favorite

0.91

 favourite

0.89

self

0.89

 newfound

0.89

Activations Density 0.325%

pronouns indicating possession or belonging

possessive pronouns and related restrictions

No Comments

No Known Activations