INDEX

Explanations

pronouns followed by possessive pronouns and possessive pronouns with nouns

oai_token-act-pair · gpt-3.5-turbo

possessive pronouns indicating ownership or belonging

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

eers

-0.89

wrap

-0.79

inctions

-0.78

eus

-0.73

zzle

-0.72

etsk

-0.72

ypes

-0.72

adata

-0.72

netflix

-0.71

Downloadha

-0.70

POSITIVE LOGITS

own

1.55

 predecessors

1.14

 respective

1.07

 beloved

1.05

 newfound

1.03

 choosing

1.02

 surroundings

0.99

 contemporaries

0.99

Own

0.97

 predecessor

0.97

Activations Density 0.182%

pronouns followed by possessive pronouns and possessive pronouns with nouns

possessive pronouns indicating ownership or belonging

No Comments

No Known Activations