INDEX

Explanations

terms related to conventions and standards

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 '\\;'

-0.71

 doInBackground

-0.64

principalTable

-0.63

 MaterialApp

-0.62

 financement

-0.61

IntoConstraints

-0.59

MethodManager

-0.57

ModelSerializer

-0.57

($__

-0.56

UnsafeEnabled

-0.56

POSITIVE LOGITS

 usual

1.57

 conventional

1.43

 Usual

1.43

usual

1.42

 customary

1.40

 traditional

1.39

 normal

1.39

 typical

1.39

 ordinary

1.36

Usual

1.35

Activations Density 0.386%

terms related to conventions and standards

No Comments

No Known Activations