INDEX

Explanations

phrases that categorize or specify types and kinds of things

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

 tremors

-0.73

 adjourn

-0.72

 grossesse

-0.69

 Geophysics

-0.69

 cardiaque

-0.69

 femur

-0.68

 évêque

-0.68

 hypotension

-0.68

 foramen

-0.67

 viime

-0.67

POSITIVE LOGITS

 types

1.00

 type

0.99

 Type

0.95

 getType

0.92

typeOf

0.88

 TYPE

0.88

 kinds

0.83

 Types

0.82

 tipo

0.82

TYPE

0.81

Activations Density 0.177%

phrases that categorize or specify types and kinds of things

No Comments

No Known Activations