INDEX

Explanations

technical terms and identifiers related to programming and data APIs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

Izvori

-0.44

 press

-0.44

 clínicas

-0.42

dí

-0.41

చు

-0.41

Decrease

-0.41

 velg

-0.41

尼斯

-0.40

press

-0.40

The

-0.40

POSITIVE LOGITS

GIVEREF

0.79

SharedCtor

0.77

RegressionTest

0.76

ulemon

0.74

 AppCompatTheme

0.68

يكب

0.67

NamedQueries

0.66

delwed

0.66

."</

0.65

 getchar

0.64

Activations Density 0.277%

technical terms and identifiers related to programming and data APIs

No Comments

No Known Activations