INDEX

Explanations

the term "ins" and variations of it in various contexts and forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Мексичка

-0.91

Portály

-0.70

DoubleQuotes

-0.62

 Beller

-0.62

XmlAccessType

-0.60

endpush

-0.60

 Cleary

-0.59

Fir

-0.59

ய்ய

-0.59

 corrector

-0.58

POSITIVE LOGITS

ins

0.70

ston

0.65

ins

0.64

;">

0.59

://"

0.59

 pisos

0.54

tispiece

0.54

STON

0.51

stones

0.51

最快更新

0.51

Activations Density 0.173%

the term "ins" and variations of it in various contexts and forms

No Comments

No Known Activations