INDEX

Explanations

terms related to pulse justification and measurement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_mlp_out

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

 pulse

-0.71

 himo

-0.69

 justify

-0.68

*/].

-0.65

 EClass

-0.65

 BoxFit

-0.63

EndGlobalSection

-0.63

AndEndTag

-0.60

rungsseite

-0.59

NameInMap

-0.59

POSITIVE LOGITS

 parlé

0.57

 parallèle

0.56

 secondaires

0.54

 StringVar

0.54

 étoit

0.54

 professionali

0.53

 obé

0.52

 rembour

0.51

ঙ্গ

0.51

 permanentes

0.50

Activations Density 0.524%

terms related to pulse justification and measurement

No Comments

No Known Activations