INDEX

Explanations

numerical identifiers, possibly related to legal or procedural citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

UnsafeEnabled

-0.71

ContentAlignment

-0.64

oredCriteria

-0.60

NgModule

-0.58

cycline

-0.56

SequentialGroup

-0.56

openSession

-0.55

InjectAttribute

-0.54

RegistryLite

-0.52

XmlAccessorType

-0.52

POSITIVE LOGITS

 pleaſure

0.85

 Majefty

0.81

 uncin

0.81

ſelf

0.80

 purpoſe

0.79

ſelves

0.77

 reaſon

0.71

 greateſt

0.71

 Reſ

0.69

 pican

0.69

Activations Density 0.055%

numerical identifiers, possibly related to legal or procedural citations

No Comments

No Known Activations