INDEX

Explanations

technical code-related terminology and syntax elements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/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.9.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

<bos>

-0.48

 klim

-0.47

 manqué

-0.46

 jugé

-0.45

 guantes

-0.43

 trumps

-0.43

 pneus

-0.41

val

-0.41

 musicales

-0.41

Smack

-0.40

POSITIVE LOGITS

DoubleQuotes

1.09

󠁢

0.86

extAlignment

0.82

 الدولى

0.81

 MainAxisSize

0.76

 nakalista

0.76

onAttach

0.75

?',

0.75

BufferException

0.75

 FetchType

0.75

Activations Density 0.109%

technical code-related terminology and syntax elements

No Comments

No Known Activations