INDEX

Explanations

references to specific locations and names in health-related contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 الرياضيه

-0.64

FOOTNOTES

-0.56

lijks

-0.53

BASELINE

-0.52

بوابة

-0.51

 Souls

-0.51

airobi

-0.48

leit

-0.47

veis

-0.47

preet

-0.47

POSITIVE LOGITS

 Shaksp

0.71

 Shakspeare

0.68

 QtWidgets

0.64

 Dynasty

0.62

 liik

0.61

 joten

0.58

 jugé

0.58

 Cang

0.58

 ་་

0.57

 Monfieur

0.56

Activations Density 0.149%

references to specific locations and names in health-related contexts

No Comments

No Known Activations