INDEX

Explanations

references to the concept of concordance, particularly in scientific contexts

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

concordance

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

UseVisualStyle

-0.52

UserScript

-0.51

 Timmy

-0.51

 MutableLiveData

-0.50

Timmy

-0.48

 LADY

-0.47

Pah

-0.46

Lady

-0.46

 Dutchman

-0.46

vestidos

-0.45

POSITIVE LOGITS

 Concord

2.44

Concord

2.27

 concord

1.76

 Concorde

1.27

CORD

1.19

 concor

1.00

 Concordia

0.91

 Accord

0.81

corde

0.81

cord

0.77

Activations Density 0.001%

references to the concept of concordance, particularly in scientific contexts

concordance

No Comments

No Known Activations