INDEX

Explanations

questions and expressions of curiosity regarding reasons or explanations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 CreateTagHelper

-0.75

مصادر

-0.69

 estimés

-0.66

 DISPOSAL

-0.66

CrossRef

-0.66

URLException

-0.66

gonic

-0.66

Datuak

-0.64

 AssemblyCulture

-0.63

Autoritní

-0.62

POSITIVE LOGITS

why

0.92

为什么要

0.84

Why

0.83

Why

0.77

why

0.76

 atleast

0.72

Varför

0.71

为什么

0.70

 Почему

0.67

 Pourquoi

0.66

Activations Density 0.156%

questions and expressions of curiosity regarding reasons or explanations

No Comments

No Known Activations