INDEX

Explanations

alphanumeric codes or identifiers commonly used in data sets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

دانشنامهٔ

-0.68

 bonbons

-0.62

thias

-0.62

findpost

-0.61

 roul

-0.61

fromnode

-0.59

IndentedString

-0.59

 unexplo

-0.58

InSection

-0.57

）』

-0.57

POSITIVE LOGITS

reportWebVitals

0.74

 فريبيس

0.72

 QWidget

0.71

CRA

0.59

getActiveSheet

0.58

</thead>

0.58

SCA

0.57

сылкі

0.56

Referencies

0.54

TSI

0.54

Activations Density 0.023%

alphanumeric codes or identifiers commonly used in data sets

No Comments

No Known Activations