INDEX

Explanations

measurements and specifications

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

in

-0.54

-0.50

-0.48

 interface

-0.47

har

-0.47

to

-0.43

 GENERATED

-0.42

 extra

-0.42

POSITIVE LOGITS

 MessageBoxIcon

0.78

 TextInputType

0.78

 InputDecoration

0.77

 photolibrary

0.73

*++

0.72

typeorm

0.72

 Мексичка

0.71

>");

0.70

^(@)

0.70

[],

0.70

Activations Density 0.071%

measurements and specifications

No Comments

No Known Activations