INDEX

Explanations

numerical values and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 كومونز

-0.67

aarrggbb

-0.58

DebuggerNonUser

-0.57

าสตร์

-0.57

 Waray

-0.57

GETHER

-0.56

culum

-0.51

 архивлан

-0.51

endous

-0.51

 hObject

-0.50

POSITIVE LOGITS

 ninety

0.66

 Ninety

0.64

{},

0.59

DoubleQuotes

0.57

<()>

0.57

 Eighty

0.56

 reafon

0.55

عين

0.54

 arrière

0.54

 pngtree

0.53

Activations Density 0.462%

numerical values and measurements

No Comments

No Known Activations