INDEX

Explanations

the start of new document segments or paragraphs indicated by the beginning of a sequence

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

ItemBackground

-0.96

-0.91

AsUp

-0.85

aarrggbb

-0.85

 intptr

-0.78

Parcelize

-0.76

 Roskov

-0.74

PyExc

-0.74

 Италијани

-0.73

Hochspringen

-0.73

POSITIVE LOGITS

 this

0.52

this

0.52

 fallu

0.48

 fondi

0.48

 medidas

0.47

Pros

0.47

 RoutedEventArgs

0.47

0.45

 prosjek

0.45

 légale

0.44

Activations Density 0.016%

the start of new document segments or paragraphs indicated by the beginning of a sequence

No Comments

No Known Activations