INDEX

Explanations

code-related elements in programming languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

endphp

-0.65

stylers

-0.58

SuppressLint

-0.55

AccessorTable

-0.55

resizingMask

-0.52

 otomatig

-0.52

WireFormatLite

-0.51

bbons

-0.51

각주

-0.50

POI

-0.50

POSITIVE LOGITS

PathVariable

0.65

IsMutable

0.57

>>();

0.55

consulté

0.55

 Bede

0.55

 awakeFromNib

0.54

assertj

0.54

InitVars

0.53

OneToMany

0.53

iarkan

0.53

Activations Density 0.028%

code-related elements in programming languages

No Comments

No Known Activations