INDEX

Explanations

programming-related syntax, specifically focusing on callbacks and operations in code functions

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 @ 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

IntoConstraints

-0.61

DockStyle

-0.60

iſchen

-0.59

MigrationBuilder

-0.59

StoryboardSegue

-0.55

ſicht

-0.54

.*")]

-0.54

WindowConstants

-0.54

 vooz

-0.54

 AssemblyCulture

-0.54

POSITIVE LOGITS

 Gewerbe

0.35

UNDEFINED

0.32

ellido

0.31

 Indra

0.29

0.28

me

0.28

←

0.27

function

0.27

 enfance

0.26

Activations Density 0.000%

programming-related syntax, specifically focusing on callbacks and operations in code functions

<start_of_turn>user

No Comments

No Known Activations