INDEX

Explanations

instances and mentions of 'st' at various activation levels

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

er

-0.80

ar

-0.67

on

-0.64

an

-0.64

al

-0.60

en

-0.59

ers

-0.58

erne

-0.56

or

-0.55

ه

-0.55

POSITIVE LOGITS

MLLoader

0.76

IGraphics

0.69

 OnTriggerEnter

0.58

pannt

0.56

jfree

0.56

جمعیت

0.56

 cohomology

0.56

MemoryWarning

0.54

enregistrement

0.53

onAttach

0.53

Activations Density 0.262%

instances and mentions of 'st' at various activation levels

No Comments

No Known Activations