INDEX

Explanations

technical terminology related to deep learning and biological processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Билгалдахарш

-0.60

 विश्वसनीयता

-0.47

 comuniques

-0.46

новниш

-0.45

lielmo

-0.43

 typelib

-0.42

FunctionFlags

-0.42

StoryboardSegue

-0.41

قایناقلار

-0.41

InitVars

-0.40

POSITIVE LOGITS

 deep

0.83

 Deeper

0.81

 deeper

0.76

 DEEP

0.71

 Deep

0.70

 diep

0.69

 profondo

0.66

DEEP

0.65

deep

0.65

Deep

0.65

Activations Density 1.726%

technical terminology related to deep learning and biological processes

No Comments

No Known Activations