INDEX

Explanations

terms related to research methodology and data management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

лки

-0.41

 Head

-0.40

Ty

-0.40

 Shout

-0.40

 Cons

-0.39

+:+

-0.39

staticmethod

-0.39

տ

-0.38

 which

-0.38

legen

-0.38

POSITIVE LOGITS

 فريبيس

0.97

formik

0.78

 propOrder

0.77

Jeografia

0.72

PostInfinity

0.71

 EconPapers

0.71

RenderAtEndOf

0.70

 الحره

0.69

 nakalista

0.66

 AssemblyTitle

0.66

Activations Density 0.959%

terms related to research methodology and data management

No Comments

No Known Activations