INDEX

Explanations

terms related to sensors and their functionality

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

 aikaa

-0.94

IFICACIONES

-0.82

ientôt

-0.79

 éché

-0.75

ilead

-0.74

intenance

-0.72

AsUp

-0.71

RTLE

-0.71

atisfaction

-0.70

 natale

-0.69

POSITIVE LOGITS

 sensors

2.15

 sensor

2.10

 Sensor

2.00

 Sensors

1.96

Sensor

1.81

 SENSOR

1.73

sensor

1.65

Sensors

1.64

sensors

1.59

SENSOR

1.51

Activations Density 0.083%

terms related to sensors and their functionality

No Comments

No Known Activations