INDEX

Explanations

terms related to scientific classifications and biological processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

now

-0.44

 perhaps

-0.41

so

-0.41

 therefore

-0.40

Tetapi

-0.39

not

-0.36

 localObject

-0.36

 this

-0.35

be

-0.35

 just

-0.35

POSITIVE LOGITS

Tikang

0.90

ScopeManager

0.87

InjectAttribute

0.85

ftagPool

0.85

цездатний

0.83

OGND

0.80

<unused43>

0.80

<unused42>

0.79

<unused41>

0.79

<pad>

0.78

Activations Density 1.133%

terms related to scientific classifications and biological processes

No Comments

No Known Activations