INDEX

Explanations

references to home-related terms or concepts

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

home and subsequent words

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

BufferException

-0.59

CppMethod

-0.59

quelize

-0.59

djangoproject

-0.58

Географиясе

-0.57

lgari

-0.56

 Slick

-0.55

VolleyError

-0.55

hoeddwyd

-0.54

<?

-0.54

POSITIVE LOGITS

Home

1.19

home

1.16

 home

1.15

 Home

1.04

HOME

0.97

 HOME

0.96

 HomeController

0.81

 homes

0.78

homes

0.77

Homes

0.77

Activations Density 0.028%

references to home-related terms or concepts

home and subsequent words

No Comments

No Known Activations