INDEX

Explanations

phrases indicating negation or resistance

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

not only

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

 InputDecoration

-0.55

 whatever

-0.50

DockStyle

-0.47

HtmlAttribute

-0.47

 AttributeError

-0.47

 maybe

-0.46

whatever

-0.45

WireFormat

-0.45

hyrchwyd

-0.45

 eventually

-0.44

POSITIVE LOGITS

pexpr

0.45

 autorytatywna

0.42

 lisäksi

0.40

withIdentifier

0.40

 transfieras

0.40

waitKey

0.39

 hanem

0.38

 بلکه

0.38

 cherchés

0.38

 farlo

0.37

Activations Density 0.021%

phrases indicating negation or resistance

not only

No Comments

No Known Activations