INDEX

Explanations

specific names or identifiers associated with initialization processes in programming contexts

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

initializer lists

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

UITableViewCell

-0.53

glMatrixMode

-0.52

webView

-0.44

TCP

-0.44

queous

-0.43

tcp

-0.42

RectangleBorder

-0.42

Tcp

-0.42

outcome

-0.41

Royaume

-0.41

POSITIVE LOGITS

 Holt

0.96

Holt

0.93

 Alberto

0.84

Alberto

0.75

initializer

0.73

JMS

0.61

 Nora

0.61

MessageState

0.59

 Elias

0.59

alberto

0.57

Activations Density 0.005%

specific names or identifiers associated with initialization processes in programming contexts

initializer lists

No Comments

No Known Activations