INDEX

Explanations

references to the term "zero" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

————————————————

-0.88

rdı

-0.80

ので

-0.74

 pinulongan

-0.72

 actuaciones

-0.69

->___

-0.67

vell

-0.67

 schia

-0.66

Rodriguez

-0.66

-0.64

POSITIVE LOGITS

nships

0.77

 Ceres

0.77

Bism

0.75

jsonwebtoken

0.75

 Milestone

0.74

Raz

0.73

 Fara

0.72

enciaga

0.71

 Kese

0.71

NEA

0.70

Activations Density 0.109%

references to the term "zero" in various contexts

No Comments

No Known Activations