INDEX

Explanations

punctuation marks and delimiters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sánchez

-0.79

 stiefel

-0.76

 rodríguez

-0.72

 fernández

-0.68

 wikipagina

-0.68

 vixion

-0.68

 Perſ

-0.67

İY

-0.67

 Anſ

-0.66

 “¿

-0.64

POSITIVE LOGITS

transQ

0.81

FailureListener

0.81

 nakalista

0.78

featureID

0.72

)))))

0.71

InjectAttribute

0.70

RegressionTest

0.70

])]

0.70

UnusedPrivate

0.69

 Designers

0.69

Activations Density 0.175%

punctuation marks and delimiters

No Comments

No Known Activations