INDEX

Explanations

statistical measurements and values in research-related contexts

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

Numerical ranges or ratios

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

featureID

-0.57

WithIOException

-0.47

webElementGuid

-0.46

 >=",

-0.46

FunctionFlags

-0.45

 &___

-0.44

expandindo

-0.43

 viewType

-0.41

AddTagHelper

-0.41

 Wiktionnaire

-0.41

POSITIVE LOGITS

 beträgt

0.74

 amounted

0.73

 wynosi

0.71

 составляет

0.69

 состави

0.66

 lautet

0.66

 ranged

0.62

 betrug

0.60

 totaled

0.60

 reaches

0.55

Activations Density 0.777%

statistical measurements and values in research-related contexts

Numerical ranges or ratios

No Comments

No Known Activations