INDEX

Explanations

narrative elements and expressions of personal reflection

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

you guess, see, suspect

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

 média

-0.48

 Winaray

-0.47

ariConfig

-0.47

GEBURTSDATUM

-0.46

 MediatR

-0.45

 anſ

-0.44

Akan

-0.44

 themſelves

-0.42

 diſt

-0.42

britanni

-0.42

POSITIVE LOGITS

 snippetHide

0.56

//

0.45

 NSCoder

0.41

 JUGA

0.39

 نکنید

0.36

 kami

0.36

 Whig

0.35

 <>",

0.35

 initComponents

0.34

 AssemblyTitle

0.34

Activations Density 0.043%

narrative elements and expressions of personal reflection

you guess, see, suspect

No Comments

No Known Activations