INDEX

Explanations

mathematical expressions or structures involving variables and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 nahilalakip

-0.73

IsContent

-0.66

脚注の使い方

-0.63

 समीक्षक

-0.62

Datuak

-0.62

RenderAtEndOf

-0.60

InSection

-0.58

awtextra

-0.58

 ModelExpression

-0.57

 Discharge

-0.57

POSITIVE LOGITS

 Photocase

0.46

RTSC

0.43

 médicaux

0.42

 Савезне

0.42

wpdb

0.42

 actrice

0.42

ancies

0.42

 ressemb

0.42

msgs

0.42

olz

0.41

Activations Density 0.383%

mathematical expressions or structures involving variables and functions

No Comments

No Known Activations