INDEX

Explanations

references to spatial positions and relationships within a structure or system

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

-0.63

an

-0.57

 actually

-0.53

at

-0.52

in

-0.51

 cherchez

-0.50

 regionales

-0.50

 soyez

-0.50

 Klasse

-0.48

not

-0.47

POSITIVE LOGITS

 елның

1.02

PerformLayout

0.90

 AssemblyVersion

0.84

SharedDtor

0.83

BeginInit

0.82

<?

0.81

 חיצוניים

0.79

 ExecuteAsync

0.77

 oprot

0.75

 '\\;'

0.75

Activations Density 0.334%

references to spatial positions and relationships within a structure or system

No Comments

No Known Activations