INDEX

Explanations

historical references related to specific time periods and notable figures

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

ordinal numbers and centuries

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

ロウィン

-0.79

MigrationBuilder

-0.78

MessageTagHelper

-0.77

[@BOS@]

-0.76

<unused14>

-0.76

<unused41>

-0.75

<unused42>

-0.75

<unused23>

-0.75

<unused8>

-0.75

<unused17>

-0.75

POSITIVE LOGITS

 eighteenth

0.30

 desco

0.27

 XVIII

0.25

協会

0.25

 proto

0.24

teg

0.23

 lime

0.23

 состави

0.22

minipage

0.22

Bic

0.22

Activations Density 0.067%

historical references related to specific time periods and notable figures

ordinal numbers and centuries

No Comments

No Known Activations