INDEX

Explanations

references to time and yearly reflections

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

<start_of_turn> user

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

[:,:,

-0.39

ukone

-0.38

žně

-0.37

(:,:,

-0.35

Искәрмәләр

-0.35

 Dami

-0.35

 prétend

-0.34

科

-0.34

 APIs

-0.34

 bese

-0.34

POSITIVE LOGITS

tvguidetime

0.73

SharedCtor

0.54

enumii

0.52

DIPSETTING

0.52

Transkript

0.51

 Infórmanos

0.50

PerformLayout

0.50

 nahilalakip

0.50

InvalidProtocol

0.49

 typelib

0.49

Activations Density 0.008%

references to time and yearly reflections

<start_of_turn> user

No Comments

No Known Activations