INDEX

Explanations

scientific symbols and variables, particularly those related to biochemical processes and equations

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

 χρόν

-0.78

?\\

-0.71

\_\_

-0.69

\"

-0.69

 εικό

-0.68

Ă

-0.66

ï

-0.66

udadera

-0.65

enderror

-0.65

 μαύ

-0.64

POSITIVE LOGITS

α

1.73

β

1.70

κ

1.59

β

1.58

α

1.58

σ

1.57

π

1.56

γ

1.50

σ

1.48

λ

1.47

Activations Density 0.142%

scientific symbols and variables, particularly those related to biochemical processes and equations

No Comments

No Known Activations