INDEX

Explanations

various punctuation marks and symbols

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

SerializedSize

-0.81

 كومونز

-0.78

RUnlock

-0.76

 hefyd

-0.75

ArgsConstructor

-0.73

 Вікіпе

-0.72

 esternos

-0.71

bootstrapcdn

-0.70

quelize

-0.68

leiter

-0.68

POSITIVE LOGITS

::::

1.08

いる

0.93

出版年

0.86

::::::::

0.86

któ

0.82

:::

0.80

허

0.77

????????

0.76

sertation

0.75

Davies

0.72

Activations Density 0.196%

various punctuation marks and symbols

No Comments

No Known Activations