INDEX

Explanations

scientific terminology, particularly in the context of physics and engineering research

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

 nakalista

-0.61

 surla

-0.57

ioutil

-0.48

vaadin

-0.44

ската

-0.44

 compositional

-0.43

 Palgrave

-0.43

 comparative

-0.43

ácti

-0.43

 differentially

-0.43

POSITIVE LOGITS

 يتيمه

0.85

AnchorStyles

0.73

 kasarigan

0.73

setVerticalGroup

0.72

tagHelperRunner

0.68

 Réponses

0.66

 NSCoder

0.65

RUnlock

0.64

ecap

0.63

SELF

0.63

Activations Density 0.533%

scientific terminology, particularly in the context of physics and engineering research

No Comments

No Known Activations