INDEX

Explanations

references to methodologies and descriptions of computations or calculations in research contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

iVar

-0.52

Ã

-0.49

 doors

-0.48

 pick

-0.47

olom

-0.47

olt

-0.47

leda

-0.47

nath

-0.46

gì

-0.46

∶

-0.46

POSITIVE LOGITS

ItemBackground

0.76

UrlResolution

0.72

MessageTagHelper

0.70

Fig

0.69

Tikang

0.69

 Appendix

0.67

 Figs

0.66

 Section

0.64

RegressionTest

0.63

 químicas

0.63

Activations Density 1.623%

references to methodologies and descriptions of computations or calculations in research contexts

No Comments

No Known Activations