INDEX

Explanations

references to programming constructs and structure

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

 AssemblyTitle

-0.93

脚注の使い方

-0.92

featureID

-0.92

=$?

-0.80

 distanciation

-0.76

complexContent

-0.73

 EconPapers

-0.73

PropertyGroup

-0.72

rrggbb

-0.72

Pratique

-0.71

POSITIVE LOGITS

OnClickListener

1.35

 OnClickListener

0.83

codegen

0.66

eqn

0.64

 aapt

0.61

onClick

0.57

 onClick

0.57

不起

0.56

newswire

0.53

 Juden

0.50

Activations Density 0.011%

references to programming constructs and structure

No Comments

No Known Activations