INDEX

Explanations

references to specific variables or parameters in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.37.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

DialogContent

-0.46

hyrchwyd

-0.45

WebMethod

-0.43

httphttps

-0.43

 ujednoznacz

-0.42

oplayer

-0.42

UrlResolution

-0.42

huriyet

-0.41

tawesome

-0.39

shadowRadius

-0.39

POSITIVE LOGITS

 invokingState

0.50



0.40

ContentAlignment

0.39

ScopeManager

0.39

 rechnen

0.38

 aberta

0.37

 MainAxisSize

0.35

sidemargin

0.35

logous

0.35

 deixe

0.34

Activations Density 0.378%

references to specific variables or parameters in scientific contexts

No Comments

No Known Activations