INDEX

Explanations

method calls or function definitions related to managing data in coding and programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

atsun

-0.47

 Lawson

-0.47

 hätten

-0.45

crites

-0.44

mêmes

-0.44

EditorBrowsable

-0.44

Hazard

-0.43

ieteur

-0.43

uegos

-0.42

 reflex

-0.42

POSITIVE LOGITS

putExtra

3.19

 resourceCulture

1.10

principalColumn

1.07

getStringExtra

1.06

GOTREF

0.90

putString

0.85

ReusableCell

0.85

SpringBootTest

0.81

rawDesc

0.81

autoconfigure

0.79

Activations Density 0.021%

method calls or function definitions related to managing data in coding and programming contexts

No Comments

No Known Activations