INDEX

Explanations

comment symbols and documentation markers within code

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

code metadata documentation

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

 Wikimedijinoj

-0.60

 Photocase

-0.59

 nakalista

-0.57

UnusedPrivate

-0.56

تقاوى

-0.56

pushFollow

-0.55

Atsauces

-0.53

SharedDtor

-0.52

хьтан

-0.52

ousands

-0.52

POSITIVE LOGITS

 surla

0.44

IBar

0.35

Nar

0.34

Nar

0.34

0.32

 cohesive

0.32

limiting

0.31

⌐

0.31

艋

0.31

Sw

0.31

Activations Density 0.018%

comment symbols and documentation markers within code

code metadata documentation

No Comments

No Known Activations