INDEX

Explanations

technical terms related to processing methods and measurements in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 imageNamed

-0.59

dfunding

-0.57

 légitime

-0.54

 useRef

-0.52

 consultato

-0.51

 doInBackground

-0.51

haped

-0.51

diğini

-0.50

ValueGenerated

-0.49

 Sử

-0.49

POSITIVE LOGITS

 methods

0.97

 method

0.87

 times

0.84

 locations

0.80

 modes

0.75

 methodology

0.75

 location

0.74

 period

0.74

 conditions

0.73

 frequency

0.73

Activations Density 1.210%

technical terms related to processing methods and measurements in scientific contexts

No Comments

No Known Activations