INDEX

Explanations

elements associated with automobile features, specifications, and performance attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 Audiodateien

-0.58

 Magnetism

-0.54

 balconies

-0.54

 Tyre

-0.49

 rabies

-0.47

raszam

-0.47

 humana

-0.47

itoria

-0.47

 Borel

-0.46

 kayaking

-0.46

POSITIVE LOGITS

 machine

1.09

 machines

1.08

 máquina

0.87

 beast

0.84

machine

0.84

machines

0.82

SourceChecksum

0.81

机器

0.80

 vehicle

0.80

 macchina

0.78

Activations Density 0.351%

elements associated with automobile features, specifications, and performance attributes

No Comments

No Known Activations