INDEX

Explanations

specific references to categories or types of entities within different contexts

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

 dõi

-0.44

راک

-0.44

tayl

-0.42

chemise

-0.42

 kapcsol

-0.42

PARAM

-0.42

łosi

-0.42

lorette

-0.41

 کش

-0.41

 Mode

-0.41

POSITIVE LOGITS

TestingModule

0.91

migrationBuilder

0.83

TypedDataSet

0.83

 ostavi

0.79

ValueStyle

0.79

 intptr

0.76

tagHelperRunner

0.74

 ExecuteAsync

0.72

GraphicsUnit

0.71

 дописавши

0.67

Activations Density 0.532%

specific references to categories or types of entities within different contexts

No Comments

No Known Activations