INDEX

Explanations

technical terminology and specifications in scientific or programming contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AndEndTag

-1.10

verwijspagina

-0.91

ArgsConstructor

-0.89

 linkovi

-0.83

 kaarangay

-0.79

FieldBuilder

-0.74

aarrggbb

-0.73

IVEREF

-0.73

SourceChecksum

-0.72

GEBURTSDATUM

-0.71

POSITIVE LOGITS

 supposed

0.76

 expected

0.73

 intended

0.62

expected

0.59

 should

0.57

Expected

0.57

 انتظار

0.54

 seharusnya

0.54

harusnya

0.54

 contract

0.53

Activations Density 0.543%

technical terminology and specifications in scientific or programming contexts

No Comments

No Known Activations