INDEX

Explanations

numerical data and values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

LookAnd

-1.09

invokeLater

-0.87

parsedMessage

-0.86

 ErrIntOverflow

-0.84

 pinulongan

-0.82

Portály

-0.82

abestanden

-0.82

RTEE

-0.80

 defaultstate

-0.78

tagHelperRunner

-0.77

POSITIVE LOGITS

 voca

0.46

",

0.46

BRON

0.46

Bron

0.43

 szen

0.43

toma

0.43

bitol

0.41

 geni

0.41

 bronz

0.41

חו

0.40

Activations Density 0.257%

numerical data and values

No Comments

No Known Activations