INDEX

Explanations

programming-related keywords and structures in code

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

declaration and assignment

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

int

-0.38

 Bewegungen

-0.35

void

-0.34

string

-0.34

int

-0.34

farwyddwr

-0.33

 TextAppearance

-0.32

String

-0.32

 bền

-0.32

Individual

-0.31

POSITIVE LOGITS

ThroughAttribute

0.69

 unknownFields

0.69

 utafitiHapana

0.66

 &___

0.63

 kaynağından

0.63

 resourceCulture

0.60

verwijspagina

0.59

الحياه

0.59

EndContext

0.59

 otomatig

0.58

Activations Density 0.146%

programming-related keywords and structures in code

declaration and assignment

No Comments

No Known Activations