INDEX

Explanations

prepositions

oai_token-act-pair · gpt-3.5-turbo

prepositions indicating location or position

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Dund

-0.79

 Province

-0.74

 Volunteers

-0.72

 Rabb

-0.69

 Provision

-0.69

 Sham

-0.68

 Franch

-0.68

 Purpose

-0.68

 Mile

-0.68

 Catalog

-0.68

POSITIVE LOGITS

serv

0.77

alon

0.75

interstitial

0.73

arde

0.72

health

0.72

pan

0.72

puff

0.72

smart

0.71

eers

0.70

assembly

0.70

Activations Density 0.000%

prepositions

prepositions indicating location or position

No Comments

No Known Activations