INDEX

Explanations

assertions and contrasts in experiences or states, particularly related to perception and expectations

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

limiting outcomes or conditions

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

Hentet

-0.52

 digress

-0.48

complexContent

-0.46

 GoogleFonts

-0.46

GTCX

-0.46

RectangleBorder

-0.45

 autorytatywna

-0.45

__(/*!

-0.45

 jouet

-0.43

 kasarigan

-0.43

POSITIVE LOGITS

lottesville

0.41

 nargin

0.36

лтемелер

0.36

augmenter

0.36

lieferung

0.36

FieldNumber

0.36

 explanation

0.34

来歴

0.34

 prediction

0.34

 twar

0.34

Activations Density 0.038%

assertions and contrasts in experiences or states, particularly related to perception and expectations

limiting outcomes or conditions

No Comments

No Known Activations