INDEX

Explanations

prepositions indicating location or direction

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "on" and related prepositional phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 Ramos

-0.85

neys

-0.71

laws

-0.65

ledge

-0.63

 Philly

-0.63

resses

-0.62

otiation

-0.62

 fert

-0.61

ises

-0.61

 bullets

-0.61

POSITIVE LOGITS

ĸļ

0.97

MpServer

0.90

cffffcc

0.87

BuyableInstoreAndOnline

0.77

OME

0.76

atural

0.73

 originally

0.72

ategory

0.71

 previously

0.71

 censored

0.71

Activations Density 0.000%

prepositions indicating location or direction

occurrences of the word "on" and related prepositional phrases

No Comments

No Known Activations