INDEX

Explanations

references to programming language imports and package declarations

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

dflare

-0.68

 snippetHide

-0.57

quelize

-0.53

cloudflare

-0.53

tvguidetime

-0.51

fhir

-0.50

Blazor

-0.48

 kubernetes

-0.47

 Jupyter

-0.47

 Toxicological

-0.47

POSITIVE LOGITS

 connexes

0.67

urion

0.60

 Arkivert

0.59

Referencias

0.58

udine

0.57

inoma

0.56

Datuak

0.55

("#{

0.54

XML

0.54

ibol

0.54

Activations Density 0.198%

references to programming language imports and package declarations

No Comments

No Known Activations