INDEX

Explanations

pronouns showing ownership or possession

oai_token-act-pair · gpt-3.5-turbo

possessive pronouns and expressions of ownership or association

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

pedia

-0.71

pmwiki

-0.65

 Shall

-0.63

lis

-0.62

ozy

-0.61

 coroner

-0.61

 Calculator

-0.61

Reviewer

-0.61

Leaks

-0.61

apa

-0.60

POSITIVE LOGITS

own

1.20

own

0.94

 possessions

0.86

 belongings

0.83

 allotted

0.82

OWN

0.82

self

0.82

 income

0.81

Own

0.79

 ancestry

0.77

Activations Density 0.110%

pronouns showing ownership or possession

possessive pronouns and expressions of ownership or association

No Comments

No Known Activations