INDEX

Explanations

numbers representing quantities or ranges

oai_token-act-pair · gpt-3.5-turbo

phrases that express quantities or estimates involving ranges

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eval

-0.72

ires

-0.68

eless

-0.68

ocrat

-0.62

 Cycling

-0.62

 Haku

-0.62

ired

-0.62

 Reporter

-0.61

ergic

-0.61

 palp

-0.60

POSITIVE LOGITS

chard

1.18

acle

1.17

ifice

1.10

ific

1.08

acles

1.07

acular

1.05

nam

1.05

lando

1.02

chid

1.02

thodox

0.94

Activations Density 0.082%

numbers representing quantities or ranges

phrases that express quantities or estimates involving ranges

No Comments

No Known Activations