INDEX

Explanations

terms related to calculating and calculations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 समीक्षाएं

-0.71

 Broom

-0.69

 resourceCulture

-0.68

 Goodman

-0.66

Gemeinden

-0.65

hoeddwyd

-0.64

 Yorke

-0.63

 Bona

-0.63

 Homme

-0.62

moreland

-0.62

POSITIVE LOGITS

 calculate

1.74

 calculations

1.72

 calculation

1.64

 Calculations

1.64

 calculating

1.63

 calculated

1.58

calculate

1.56

 Calculate

1.56

 calculates

1.55

 Calculating

1.55

Activations Density 0.153%

terms related to calculating and calculations

No Comments

No Known Activations