INDEX

Explanations

terms and references related to technical events and structures in a specified domain

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DoubleQuotes

-0.57

}$}

-0.48

россий

-0.44

@"/

-0.43

[*]

-0.43

 naselje

-0.42

 Emits

-0.41

und

-0.41

 мѣ

-0.41

 منتخب

-0.40

POSITIVE LOGITS

 ſtand

0.88

 himſelf

0.86

 itſelf

0.85

IntoConstraints

0.83

 myſelf

0.83

 pleaſure

0.82

 uſed

0.82

 anſ

0.81

 themſelves

0.80

 houſe

0.79

Activations Density 3.798%

terms and references related to technical events and structures in a specified domain

No Comments

No Known Activations