INDEX

Explanations

terms related to perception and awareness

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

rungsseite

-0.58

 calldata

-0.56

artifactId

-0.55

reactstrap

-0.55

Formik

-0.52

 habitudes

-0.52

 astore

-0.51

featureID

-0.50

typeparam

-0.50

devtools

-0.50

POSITIVE LOGITS

disposing

0.60

NullCheck

0.60

 ThemeData

0.57

 casó

0.55

MathML

0.53

 dane

0.53

ー

0.53

ExecuteReader

0.51

躇

0.50

 करने

0.50

Activations Density 0.584%

terms related to perception and awareness

No Comments

No Known Activations