INDEX

Explanations

programming constructs and language elements in code

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

code snippets and errors

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

 ویکی‌پدیا

-0.29

åter

-0.27

 requests

-0.26

ム

-0.26

用意

-0.25

Request

-0.24

rungsseite

-0.24

 veren

-0.24

 féd

-0.24

 Request

-0.24

POSITIVE LOGITS

StoryboardSegue

0.77

 HasFactory

0.72

 disambiguazione

0.68

 XCTest

0.67

findpost

0.65

 Numerade

0.59

providedIn

0.58

FormTagHelper

0.58

+#+

0.58

 виправивши

0.57

Activations Density 0.078%

programming constructs and language elements in code

code snippets and errors

No Comments

No Known Activations