INDEX

Explanations

the name "M" with varying levels of activation

oai_token-act-pair · gpt-3.5-turbo

mentions or references to the letter "M"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ãĤ¡

-0.81

 Eleven

-0.74

 fashioned

-0.70

 tips

-0.64

 yours

-0.63

 tipped

-0.63

 center

-0.62

 briefs

-0.62

 caps

-0.61

 Beyond

-0.60

POSITIVE LOGITS

useum

1.07

uppet

1.05

asonic

1.04

insk

1.03

ormon

1.01

ISSION

1.00

ixed

0.99

asters

0.99

ortal

0.98

astered

0.98

Activations Density 0.033%

the name "M" with varying levels of activation

mentions or references to the letter "M"

No Comments

No Known Activations