INDEX

Explanations

programming constructs related to function definitions and calls

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 kasarigan

-0.88

contentLoaded

-0.76

 Reſ

-0.70

 ſche

-0.69

 ſeveral

-0.69

webElementXpaths

-0.67

 الرياضيه

-0.65

 Diſ

-0.65

出版年

-0.64

 AssemblyCulture

-0.64

POSITIVE LOGITS

posedge

0.64

tonode

0.59

raltar

0.55

featureID

0.55

ActivityCompat

0.54

RegressionTest

0.53

 birlikte

0.52

 doInBackground

0.51

forhold

0.51

 Call

0.50

Activations Density 0.129%

programming constructs related to function definitions and calls

No Comments

No Known Activations