INDEX

Explanations

sets of nested or structured mathematical expressions

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

$\kappa_{\mathrm{ex}}$, $\eta_{\mathrm{esc}}$, $\eta_{\mathrm{in}}$, $\mathrm{opt}$

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

 MainAxisSize

-0.87

 فريبيس

-0.77

IntoConstraints

-0.77

iſen

-0.73

 समीक्षाओं

-0.73

tvguidetime

-0.70

guiente

-0.69

rungsseite

-0.69

PerformLayout

-0.68

 defaultstate

-0.68

POSITIVE LOGITS

0.78

<strong>

0.51

0.50

<b>

0.49

<em>

0.44

พาะ

0.43

 sickly

0.43

 nanny

0.43

 inexorable

0.42

{'

0.41

Activations Density 0.032%

sets of nested or structured mathematical expressions

$\kappa_{\mathrm{ex}}$, $\eta_{\mathrm{esc}}$, $\eta_{\mathrm{in}}$, $\mathrm{opt}$

No Comments

No Known Activations