INDEX

Explanations

repeated numeric patterns or sequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

#+#

-0.79

 keli

-0.77

########.

-0.76

 Paglinawan

-0.75

]};

-0.73

 scher

-0.72

king

-0.68

 Dati

-0.64

 ujednoznacz

-0.64

着头

-0.64

POSITIVE LOGITS

atorze

0.84

 ۱۹

0.82

berdayakan

0.73

antaranya

0.71

ethene

0.70

 २०

0.70

 nineteen

0.70

 strands

0.69

inspace

0.67

teenth

0.66

Activations Density 0.376%

repeated numeric patterns or sequences

No Comments

No Known Activations