INDEX

Explanations

code documentation elements and metadata annotations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

<bos>

-0.47

جستارهای

-0.45

-0.43

见

-0.43

 secretos

-0.42

las

-0.41

HIDE

-0.40

 comp

-0.40

setResult

-0.39

 ће

-0.39

POSITIVE LOGITS

Tikang

1.01

 <<<<<<<<<<<<<<

0.92

DebuggerNonUser

0.90

ContentAsync

0.85

rungsseite

0.84

Personensuche

0.82

__(/*!

0.82

 مشين

0.81

mybatisplus

0.81

abestanden

0.77

Activations Density 0.020%

code documentation elements and metadata annotations

No Comments

No Known Activations