INDEX

Explanations

phrases related to specific locations or regions

oai_token-act-pair · gpt-3.5-turbo

mentions of "in" that indicate locations or contexts within various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

0000000000000000

-0.62

tar

-0.61

eal

-0.60

MpServer

-0.60

agine

-0.60

ãĤ³

-0.59

#$

-0.59

SourceFile

-0.58

tal

-0.58

POSITIVE LOGITS

 general

1.54

 particular

1.43

efficiency

1.06

effic

1.00

 America

0.99

clusions

0.99

 nutshell

0.96

clus

0.94

 relation

0.90

versions

0.87

Activations Density 0.243%

phrases related to specific locations or regions

mentions of "in" that indicate locations or contexts within various subjects

No Comments

No Known Activations