INDEX

Explanations

programming-related documentation or comments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

fromnode

-0.55

.*")]

-0.49

GenerationType

-0.49

setVerticalGroup

-0.47

GraphicsUnit

-0.47

verifyException

-0.46

+#+

-0.44

 betweenstory

-0.44

AutoField

-0.43

EndGlobalSection

-0.43

POSITIVE LOGITS

 ſind

0.63

 kasarigan

0.61

 auffi

0.58

 queſta

0.57

$_(

0.53

 feroit

0.52

 müſſen

0.52

 miniaturka

0.52

$_"

0.52

 ſein

0.52

Activations Density 0.004%

programming-related documentation or comments

No Comments

No Known Activations