INDEX

Explanations

technical jargon related to statistical modeling and parameters

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

Followed by "value" or "values"

np_acts-logits-general · gemini-2.0-flash

values and parameters

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.20.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

المناصب

-0.54

UserScript

-0.53

FormTagHelper

-0.50

 переписи

-0.48

oredCriteria

-0.48

DeleteBehavior

-0.48

########.

-0.48

ItemLayout

-0.46

ftagPool

-0.45

ViewImports

-0.44

POSITIVE LOGITS

 value

3.31

value

2.98

 values

2.95

 Value

2.74

 VALUE

2.67

Value

2.65

 Values

2.57

 valeur

2.55

VALUE

2.53

values

2.50

Activations Density 0.976%

technical jargon related to statistical modeling and parameters

Followed by "value" or "values"

values and parameters

No Comments

No Known Activations