INDEX

Explanations

terms related to confounding variables and statistical terms associated with findings

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

words starting with conf

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

AnimationsModule

-0.64

QMetaType

-0.61

RectangleBorder

-0.61

 chré

-0.59

 vété

-0.59

WebVitals

-0.58

 MainAxisSize

-0.57

 pitié

-0.57

 esternos

-0.56

ThroughAttribute

-0.55

POSITIVE LOGITS

 conf

2.06

 Conf

1.91

Conf

1.83

conf

1.77

 CONF

1.59

CONF

1.41

 Confessions

1.17

 confocal

1.05

 Confession

1.03

 confession

0.99

Activations Density 0.016%

terms related to confounding variables and statistical terms associated with findings

words starting with conf

No Comments

No Known Activations