INDEX

Explanations

references to programming terminology and data structures

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

</b>

-0.98

</i>

-0.77

 Ashford

-0.72

 cervello

-0.70

 Clow

-0.69

 Floren

-0.69

blueprint

-0.67

//////////////

-0.67

ecore

-0.66

 Precambrian

-0.66

POSITIVE LOGITS

 propOrder

0.94

tio

0.87

 Titi

0.87

Ti

0.86

Tid

0.85

 Tide

0.81

 rooster

0.79

tilia

0.79

 Spro

0.79

tid

0.79

Activations Density 0.568%

references to programming terminology and data structures

No Comments

No Known Activations