INDEX

Explanations

references to benefits

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

"benefit"

np_acts-logits-general · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

autorest

-0.56

 surla

-0.54

 مشين

-0.51

цездатний

-0.48

 EconPapers

-0.46

insics

-0.45

chartInstance

-0.45

raulic

-0.44

cy

-0.42

POSITIVE LOGITS

 Benefit

0.66

 Benefits

0.61

Benefit

0.61

 benefit

0.58

Benef

0.58

benefit

0.57

Benefits

0.57

 benefits

0.55

 Benef

0.55

Beneficios

0.52

Activations Density 0.029%

references to benefits

"benefit"

No Comments

No Known Activations