INDEX

Explanations

programming function definitions

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

<start_of_turn>user prefix

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

FilterChain

-0.60

 Roskov

-0.59

exitRule

-0.56

 <>",

-0.54

'{@

-0.54

 protoimpl

-0.52

 Autorizaciones

-0.51

ViewFeatures

-0.50

GTCX

-0.49

 createSlice

-0.48

POSITIVE LOGITS

providedIn

0.57

{*}

0.46

TemporalType

0.42

Gdx

0.41

noinspection

0.40

yship

0.39

衫

0.38

Malformed

0.38

ylvan

0.37

strokeStyle

0.37

Activations Density 0.000%

programming function definitions

<start_of_turn>user prefix

No Comments

No Known Activations