INDEX

Explanations

terms related to mathematical concepts and operations in data reconstruction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

kew

-0.49

 Oliva

-0.46

InlineData

-0.43

Vak

-0.43

istika

-0.42

 Huma

-0.41

Vak

-0.41

keb

-0.41

او

-0.40

Dib

-0.40

POSITIVE LOGITS

 optimization

0.86

 raiſ

0.86

 optimizer

0.84

 Optimization

0.83

 iterative

0.83

 optim

0.81

 optimisation

0.81

 estimés

0.80

 minimization

0.80

 Optimize

0.79

Activations Density 1.573%

terms related to mathematical concepts and operations in data reconstruction

No Comments

No Known Activations