INDEX

Explanations

elements related to complex mathematical expressions or formulas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Identyfik

-0.78

SourceChecksum

-0.73

sizeCache

-0.71

UnusedPrivate

-0.71

Vidite

-0.71

 AssemblyCulture

-0.70

.",

-0.65

 >=",

-0.65

@[+][

-0.65

')));

-0.65

POSITIVE LOGITS

 metres

0.74

0.72

PM

0.64

0.62

0.56

pm

0.56

am

0.55

 metre

0.52

Activations Density 0.397%

elements related to complex mathematical expressions or formulas

No Comments

No Known Activations