INDEX

Explanations

references to academic publications and collaborative research efforts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120

Prompts (Dashboard)

24,576 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

 '\\;'

-0.71

 AssemblyCulture

-0.63

 <<<<<<<<<<<<<<

-0.59

CloseOperation

-0.59

 BoxFit

-0.56

AsUp

-0.55

TagHelper

-0.54

 Arrows

-0.54

 RISERVATA

-0.53

RetentionPolicy

-0.52

POSITIVE LOGITS

webElementXpaths

0.60

CrossRef

0.46

 competencia

0.42

principalColumn

0.42

WriteBarrier

0.41

GeneratedMessage

0.38

 księ

0.37

 integridad

0.37

 pokoju

0.37

 subterrá

0.36

Activations Density 0.330%

references to academic publications and collaborative research efforts

No Comments

No Known Activations