INDEX

Explanations

references to internal processes or structures in a technical context

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

 InputDecoration

-0.76

addGap

-0.71

 HttpNotFound

-0.68

oredCriteria

-0.65

 createSlice

-0.65

 groupBox

-0.64

 useAppContext

-0.63

ChildScrollView

-0.62

AutoField

-0.60

onOptions

-0.60

POSITIVE LOGITS

Šaltiniai

0.39

Хьажоргаш

0.37

 internetowa

0.34

Билгалдахарш

0.33

 estekak

0.32

melada

0.31

下载附件

0.31

 Evan

0.31

 aapt

0.31

hoeddwyd

0.31

Activations Density 0.000%

references to internal processes or structures in a technical context

No Comments

No Known Activations