INDEX

Explanations

references to file paths, URLs, and methods used in programming

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

Code snippets or file paths

np_acts-logits-general · gemini-2.0-flash

path delimiters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 codice

-0.53

 Wicidata

-0.52

PullParser

-0.51

Serviço

-0.49

یکر

-0.49

нь

-0.47

beiros

-0.46

bitat

-0.44

BGP

-0.43

 Objec

-0.42

POSITIVE LOGITS

admin

0.86

Admin

0.85

 admin

0.84

 Admin

0.77

 home

0.74

 HomeController

0.71

 ADMIN

0.68

 administration

0.67

home

0.67

 administrative

0.67

Activations Density 0.119%

references to file paths, URLs, and methods used in programming

Code snippets or file paths

path delimiters

No Comments

No Known Activations