INDEX

Explanations

terms related to biological processes and connections in a computational context

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

states and outcomes

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

出版年

-0.65

VersionUID

-0.65

XmlAccessorType

-0.60

WebElementEntity

-0.59

DoubleQuotes

-0.59

RegressionTest

-0.58

InitVars

-0.57

StoryboardSegue

-0.56

AnchorTagHelper

-0.56

+#+#

-0.55

POSITIVE LOGITS

ss

0.31

 quickly

0.31

 soon

0.27

 defaultstate

0.26

 nær

0.26

 quick

0.26

 corred

0.26

 collectif

0.25

xon

0.25

stro

0.25

Activations Density 0.056%

terms related to biological processes and connections in a computational context

states and outcomes

No Comments

No Known Activations