INDEX

Explanations

technical descriptions and terms related to systems, parameters, and computational calculations

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

AndEndTag

-0.75

 social

-0.74

:✨

-0.66

ArgsConstructor

-0.61

iprot

-0.60

 sociais

-0.58

 initComponents

-0.57

 resigning

-0.56

 saites

-0.56

 betweenstory

-0.56

POSITIVE LOGITS

 gamme

0.63

 optimum

0.63

 tolerances

0.62

YMMV

0.61

Theore

0.60

 overkill

0.60

Testing

0.59

 comercial

0.58

 optimize

0.58

 manufacturers

0.56

Activations Density 0.456%

technical descriptions and terms related to systems, parameters, and computational calculations

No Comments

No Known Activations