INDEX

Explanations

references to time-related metrics, specifically durations and anniversaries

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

<start_of_turn>user

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

faßt

-0.38

 toàn

-0.35

Parcelize

-0.33

 vorbehalten

-0.33

 laiton

-0.32

Correspondence

-0.31

dė

-0.31

 prestazioni

-0.30

 henkil

-0.30

BASEPATH

-0.30

POSITIVE LOGITS

bitField

0.56

vician

0.54

MigrationBuilder

0.49

WriteTagHelper

0.44

 ventilator

0.44

//

0.44

/*

0.44

SequentialGroup

0.44

 Godt

0.43

 defStyleAttr

0.43

Activations Density 0.028%

references to time-related metrics, specifically durations and anniversaries

<start_of_turn>user

No Comments

No Known Activations