INDEX

Explanations

phrases containing assertions or qualifications about specific subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 дописавши

-0.88

 initComponents

-0.81

:+:

-0.77

 BoxFit

-0.76

はじめに

-0.75

 autorytatywna

-0.72

onAttach

-0.71

providedIn

-0.71

#+#

-0.71

SharedDtor

-0.69

POSITIVE LOGITS

 itself

0.86

itself

0.85

 Itself

0.73

 proprement

0.70

本身

0.66

 selve

0.66

 herself

0.64

themselves

0.62

 directamente

0.60

 himself

0.60

Activations Density 0.411%

phrases containing assertions or qualifications about specific subjects

No Comments

No Known Activations