INDEX

Explanations

mentions of directions or locations associated with actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

 Namib

-0.63

 Compagn

-0.56

 Morav

-0.54

 Assad

-0.54

 Zamb

-0.54

 Transvaal

-0.53

 Lusaka

-0.51

 Netanyahu

-0.51

 baha

-0.50

 Shropshire

-0.50

POSITIVE LOGITS

بوابة

1.08

goTo

0.83

AxisAlignment

0.82

EndGlobalSection

0.78

 mxArray

0.78

errHandler

0.77

دانشنامهٔ

0.77

 goTo

0.76

 consultato

0.76

WriteBarrier

0.75

Activations Density 0.195%

mentions of directions or locations associated with actions

No Comments

No Known Activations