INDEX

Explanations

references to evaluation, assessment, and related concepts in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 butterknife

-0.69

 gober

-0.66

</h2>

-0.65

Ser

-0.63

 drop

-0.63

ar

-0.63

го

-0.62

zd

-0.62

zam

-0.61

ly

-0.60

POSITIVE LOGITS

 evaluations

1.47

 Evalu

1.45

 evalu

1.45

 evaluator

1.45

evaluated

1.36

 Evaluations

1.34

 evaluation

1.33

 evaluated

1.33

 evaluate

1.32

evaluate

1.30

Activations Density 0.096%

references to evaluation, assessment, and related concepts in various contexts

No Comments

No Known Activations