INDEX

Explanations

locations or distances

oai_token-act-pair · gpt-3.5-turbo

phrases indicating geographical locations or distances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

chrom

-0.75

rix

-0.73

URI

-0.71

impro

-0.70

IQ

-0.69

Article

-0.68

................................................................

-0.68

attribute

-0.68

unn

-0.68

gal

-0.68

POSITIVE LOGITS

 downtown

1.20

 campus

1.01

 where

1.01

 Bethlehem

0.99

 shore

0.97

 town

0.93

 headquarters

0.89

 Perth

0.88

 nearest

0.87

 bustling

0.87

Activations Density 0.112%

locations or distances

phrases indicating geographical locations or distances

No Comments

No Known Activations