INDEX

Explanations

sentences containing numbers followed by a noun

oai_token-act-pair · gpt-3.5-turbo

numeric references, especially in the context of statistical data or reports

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

DCS

-0.53

annabin

-0.50

ãĤ¨ãĥ«

-0.46

VIDEO

-0.45

cigarettes

-0.45

ãģ¾

-0.44

ãĤ±

-0.44

efe

-0.44

pmwiki

-0.43

Wr

-0.43

POSITIVE LOGITS

 however

0.73

tho

0.58

 though

0.58

 meanwhile

0.56

Pwr

0.50

 therefore

0.49

SourceFile

0.47

 ---------

0.46

 moreover

0.44

Lum

0.43

Activations Density 3.167%

sentences containing numbers followed by a noun

numeric references, especially in the context of statistical data or reports

No Comments

No Known Activations