INDEX

Explanations

terms related to various operational or functional codes and their associated properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Personensuche

-0.71

SharedDtor

-0.65

enance

-0.61

 MediatR

-0.60

 nahilalakip

-0.59

 فريبيس

-0.59

 صوتيه

-0.59

Personendaten

-0.59

 Bana

-0.58

addGap

-0.58

POSITIVE LOGITS

OCC

1.10

 Olsen

1.00

 Ogle

0.99

Oku

0.96

Ols

0.95

Ong

0.95

Ome

0.92

 Oates

0.92

 Orchard

0.92

OCS

0.91

Activations Density 0.430%

terms related to various operational or functional codes and their associated properties

No Comments

No Known Activations