INDEX

Explanations

elements related to strategic planning and priorities

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

enumerated classifications

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

RegressionTest

-0.59

 resourceCulture

-0.38

 McNeil

-0.35

defaults

-0.34

 مشين

-0.33

 Rough

-0.33

 kasarigan

-0.33

 устрой

-0.33

 СМИ

-0.32

stdc

-0.32

POSITIVE LOGITS

 ſtand

0.60

parsedMessage

0.59

 cauſe

0.56

 myſelf

0.55

ſelves

0.55

IntoConstraints

0.53

 ſhall

0.52

 doInBackground

0.52

Datuak

0.51

 becauſe

0.51

Activations Density 0.021%

elements related to strategic planning and priorities

enumerated classifications

No Comments

No Known Activations