INDEX

Explanations

legislative language related to the allowance and authorization of policies or actions

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

rules, legislation, or permissions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 során

-0.38

ellini

-0.37

gridad

-0.37

[::-

-0.36

 szak

-0.36

RTEE

-0.35

Others

-0.35

 Fanning

-0.34

row

-0.34

viewtopic

-0.34

POSITIVE LOGITS

 snippetHide

0.65

endcsname

0.61

 surla

0.59

 ujednoznacz

0.59

httphttps

0.59

ConstraintMaker

0.56

 disambiguazione

0.56

Hentet

0.55

 HasFactory

0.53

 &___

0.51

Activations Density 0.020%

legislative language related to the allowance and authorization of policies or actions

rules, legislation, or permissions

No Comments

No Known Activations