INDEX

Explanations

code-related elements and references in programming documentation

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

bibliography

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 дописавши

-0.66

findpost

-0.62

WebVitals

-0.59

 pleaſure

-0.57

ptonshire

-0.57

SequentialGroup

-0.56

InitVars

-0.56

AddTagHelper

-0.56

vacy

-0.56

DockStyle

-0.56

POSITIVE LOGITS

Становништво

0.36

 esperti

0.33

TargetApi

0.33

 صوتيه

0.30

 expertos

0.29

芥

0.29

 tộc

0.28

辞典

0.28

 Store

0.27

meler

0.27

Activations Density 0.002%

code-related elements and references in programming documentation

bibliography

No Comments

No Known Activations