INDEX

Explanations

terms related to processes and effects that disrupt or influence measurements and systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 PrintWriter

-0.47

breakdown

-0.47

 talál

-0.46

 lepto

-0.46

AccessLevel

-0.46

 Castello

-0.44

 mapStateToProps

-0.44

 least

-0.44

 Lightfoot

-0.43

 Thü

-0.43

POSITIVE LOGITS

GEBURTSDATUM

0.77

новниш

0.65

ագրություններ

0.64

mmation

0.62

 nahilalakip

0.62

bing

0.59

cable

0.58

gegangen

0.57

ring

0.56

cement

0.56

Activations Density 0.482%

terms related to processes and effects that disrupt or influence measurements and systems

No Comments

No Known Activations