INDEX

Explanations

mentions or references to the latest or newest versions of things

oai_token-act-pair · gpt-3.5-turbo

references to the most recent updates or versions of technology-related products and information

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

This neuron detects numeric software version numbers (especially those following “latest”).

oai_token-act-pair · o4-mini Triggered by @lukw63

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

alties

-0.89

erved

-0.82

fman

-0.73

hovah

-0.73

shared

-0.73

bos

-0.72

ateral

-0.72

par

-0.72

bara

-0.71

avery

-0.70

POSITIVE LOGITS

 incarnation

1.14

 iteration

1.12

 edition

1.04

 installment

1.00

 developments

0.96

 update

0.91

 batch

0.88

 editions

0.85

 arrivals

0.83

 round

0.83

Activations Density 0.022%

mentions or references to the latest or newest versions of things

references to the most recent updates or versions of technology-related products and information

This neuron detects numeric software version numbers (especially those following “latest”).

No Comments

No Known Activations