INDEX

Explanations

expressions of intent or willingness regarding actions or decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

toBeTruthy

-0.56

 puissiez

-0.55

tences

-0.55

brata

-0.53

 بيها

-0.52

 Pute

-0.48

σεων

-0.48

Argb

-0.48

 inappropriés

-0.48

ronique

-0.47

POSITIVE LOGITS

rungsseite

0.76

Hochspringen

0.65

homonymie

0.63

 InputDecoration

0.59

ejo

0.56

InteropServices

0.53

localVar

0.52

 مرئيه

0.50

afficheront

0.50

 EdgeInsets

0.49

Activations Density 0.214%

expressions of intent or willingness regarding actions or decisions

No Comments

No Known Activations