INDEX

Explanations

references to legal terms and proceedings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.20.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

 ligiloj

-0.74

 snippetHide

-0.73

TagMode

-0.71

ագրություններ

-0.70

InitVars

-0.69

 GenerationType

-0.69

 تانيه

-0.68

AddHtmlAttribute

-0.66

 AspNetCore

-0.66

ScopeManager

-0.65

POSITIVE LOGITS

has

0.55

 ecco

0.50

 announces

0.49

0.48

 lenker

0.48

but

0.46

 welcomes

0.46

できるように

0.46

Dam

0.45

 joins

0.45

Activations Density 0.702%

references to legal terms and proceedings

No Comments

No Known Activations