INDEX

Explanations

code-related syntax and structures

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

<start_of_turn>user

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

########.

-0.58

rungsseite

-0.56

帖最后由

-0.54

XmlEnum

-0.53

السكان

-0.52

PreferredItem

-0.52

EndContext

-0.51

 aDecoder

-0.50

jsxFileName

-0.49

期刊论文

-0.49

POSITIVE LOGITS

IUrlHelper

0.35

klima

0.33

Rights

0.33

QUENCE

0.32

ERVIEW

0.32

editary

0.32

 Architecture

0.31

 Gegenteil

0.31

 ComVisible

0.31

 Prés

0.31

Activations Density 0.001%

code-related syntax and structures

<start_of_turn>user

No Comments

No Known Activations