INDEX

Explanations

references to historical conflicts and violent actions involving combative forces

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

SizeF

-0.57

SPATH

-0.56

gå

-0.47

 parseFrom

-0.47

AutoScale

-0.47

тся

-0.45

trägen

-0.44

benhavn

-0.44

LayoutStyle

-0.44

 avail

-0.44

POSITIVE LOGITS

 neceff

0.72

 pleaſure

0.67

 poffe

0.63

 fhew

0.63

 fevere

0.61

 مرئيه

0.61

ſelf

0.59

ghum

0.59

 polenta

0.58

Transkript

0.58

Activations Density 0.327%

references to historical conflicts and violent actions involving combative forces

No Comments

No Known Activations