INDEX

Explanations

technical terms and concepts related to experimental research and analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

StoryboardSegue

-0.76

 Meksiku

-0.64

 NSCoder

-0.63

 actionMode

-0.61

adpleegd

-0.61

 հղումներ

-0.60

ganu

-0.60

CONSIN

-0.58

 GenerationType

-0.58

 chng

-0.58

POSITIVE LOGITS

of

0.69

 terbesar

0.53

 būs

0.48

 vardı

0.46

を

0.46

cheiben

0.44

<bos>

0.44

mişti

0.44

 słon

0.44

 của

0.43

Activations Density 0.683%

technical terms and concepts related to experimental research and analysis

No Comments

No Known Activations