INDEX

Explanations

references to medical qualifications or credentials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

NameInMap

-0.82

 CommandType

-0.68

 continúas

-0.67

ubscribe

-0.67

 Bure

-0.64

LEncoder

-0.64

TabIndex

-0.64

migrationBuilder

-0.64

HasAnnotation

-0.64

twimg

-0.64

POSITIVE LOGITS

ks

1.34

KS

0.87

chi

0.69

md

0.67

fd

0.65

MD

0.63

contentLoaded

0.62

Jeografia

0.60

MD

0.60

md

0.59

Activations Density 0.041%

references to medical qualifications or credentials

No Comments

No Known Activations