INDEX

Explanations

numerical data and statistical comparisons related to clinical features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

<eos>

-0.69

 للمعارف

-0.68

amsmath

-0.61

CppCodeGen

-0.57

bere

-0.53

grund

-0.50

 opposition

-0.48

↵↵

-0.48

 ever

-0.47

انيف

-0.46

POSITIVE LOGITS

ConstraintMaker

0.95

 initComponents

0.72

IsMutable

0.71

 dieß

0.71

ActionCreators

0.68

Efq

0.66

তথ্যসূত্র

0.66

 avoient

0.65

makeConstraints

0.65

 leſs

0.65

Activations Density 1.114%

numerical data and statistical comparisons related to clinical features

No Comments

No Known Activations