INDEX

Explanations

technical specifications and measurement details in scientific texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

msgTypes

-0.72

 AssemblyCulture

-0.67

covo

-0.56

 ProtoMessage

-0.54

 Reif

-0.54

 snippetHide

-0.53

ForType

-0.53

hart

-0.52

 Zeug

-0.51

FormTagHelper

-0.51

POSITIVE LOGITS

 absorbance

0.96

 Absorb

0.78

 wavelength

0.77

absorb

0.71

wavelength

0.66

Wavelength

0.64

 absorption

0.63

 Wavelength

0.62

 Absorption

0.62

Absor

0.61

Activations Density 0.452%

technical specifications and measurement details in scientific texts

No Comments

No Known Activations