INDEX

Explanations

names of people or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 quæ

-0.98

 Shaksp

-0.90

 Claudius

-0.82

 Shogun

-0.79

AOC

-0.77

 Monfieur

-0.77

 plugins

-0.77

 Româ

-0.76

 Bloomsbury

-0.76

Smarty

-0.75

POSITIVE LOGITS

Tim

0.76

Hozzáférés

0.75

tim

0.74

 Rangel

0.72

`;

0.71

 дописавши

0.70

MigrationBuilder

0.70

يكب

0.69

 numberWith

0.68

typeorm

0.68

Activations Density 1.854%

names of people or entities

No Comments

No Known Activations