INDEX

Explanations

words related to naming or labeling

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

instances of the word "call" in various contexts

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

naming or calling something

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

GEBURTSDATUM

-0.68

 doInBackground

-0.60

otry

-0.56

 interstate

-0.52

ImageContext

-0.52

 صوتيه

-0.51

didSet

-0.51

Hiz

-0.51

 coerci

-0.50

 Abroad

-0.50

POSITIVE LOGITS

it

0.76

addPreferredGap

0.68

 calling

0.64

 spade

0.62

blatt

0.59

 names

0.58

طقة

0.58

di

0.57

 call

0.57

 calls

0.56

Activations Density 0.023%

words related to naming or labeling

instances of the word "call" in various contexts

naming or calling something

No Comments

No Known Activations