INDEX

Explanations

patterns of specific code constructs or syntax

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

Uncommon or partial words/tokens

np_acts-logits-general · gemini-2.0-flash

ageing Booth / This order

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 Cline

-0.67

 quartiers

-0.62

 blanches

-0.61

 Baumann

-0.59

KommentareTeilen

-0.59

(@"%@",

-0.57

spesies

-0.55

 Cabral

-0.55

ември

-0.54

 personnalisé

-0.54

POSITIVE LOGITS

0.80

 فريبيس

0.75

neſs

0.72

0.68

0.67

 protoimpl

0.62

0.61

CodeAnalysis

0.60

躇

0.60

Activations Density 0.307%

patterns of specific code constructs or syntax

Uncommon or partial words/tokens

ageing Booth / This order

No Comments

No Known Activations