INDEX

Explanations

programming-related terminology and parameters

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

Oppretter snarvei

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

parsedMessage

-0.90

 AssemblyCulture

-0.78

URLException

-0.75

-------

-0.73

SharedCtor

-0.71

EDEFAULT

-0.69

principalColumn

-0.69

󠁣

-0.67

AndEndTag

-0.66

 HasFactory

-0.65

POSITIVE LOGITS

Kind

0.38

SIN

0.38

Inter

0.38

EST

0.37

Pl

0.36

ST

0.36

Ep

0.36

Sub

0.34

spr

0.34

namental

0.34

Activations Density 0.043%

programming-related terminology and parameters

Oppretter snarvei

No Comments

No Known Activations