INDEX

Explanations

function or variable declarations and their associated parameters in programming

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

programming code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IntoConstraints

-0.62

 ExecuteAsync

-0.56

 protoimpl

-0.56

GEBURTSDATUM

-0.54

 AssemblyTitle

-0.54

InstrumentedTest

-0.52

存于互联网档案馆

-0.52

 Chriftian

-0.51

]")]

-0.50

 myſelf

-0.50

POSITIVE LOGITS

us

0.36

 Lagi

0.36

 Gould

0.36

0.35

aca

0.35

Multipart

0.35

umal

0.35

anat

0.34

aser

0.34

ci

0.34

Activations Density 0.028%

function or variable declarations and their associated parameters in programming

programming code

No Comments

No Known Activations