INDEX

Explanations

programming terms and references relevant to software development

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

vegli

-0.48

 ostavi

-0.47

ніципалі

-0.46

̍t

-0.46

organisms

-0.46

 урна

-0.46

 Heuer

-0.45

 char

-0.45

 stack

-0.45

 MIND

-0.44

POSITIVE LOGITS

1.08

Mus

0.79

StoreMessageInfo

0.74

Mus

0.70

Παραπομπές

0.69

 Administrativna

0.64

0.63

Cousin

0.61

 ModelExpression

0.59

 CreateTagHelper

0.58

Activations Density 2.779%

programming terms and references relevant to software development

No Comments

No Known Activations