INDEX

Explanations

references to procedural elements or steps in scientific or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-0.44

til

-0.43

ro

-0.41

jelder

-0.41

 inteligentes

-0.40

 until

-0.39

 initially

-0.38

ry

-0.37

 till

-0.36

 skak

-0.36

POSITIVE LOGITS

InjectAttribute

1.02

:✨

0.94

CloseOperation

0.94

 ModelExpression

0.90

StoreMessageInfo

0.85

+#+

0.83

findpost

0.82

CppMethod

0.80

UnusedPrivate

0.78

PerformLayout

0.78

Activations Density 0.765%

references to procedural elements or steps in scientific or technical contexts

No Comments

No Known Activations