INDEX

Explanations

technical terms related to experimental procedures or data analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

}$.\\

-1.03

 […]

-0.98

</h3>

-0.95

 therefrom

-0.95

[…]

-0.88

}}$.

-0.88

 theirs

-0.86

.\\

-0.86

'])->

-0.86

.…

-0.84

POSITIVE LOGITS

MERCIAL

0.52

^(@)

0.49

seamnă

0.49

وفة

0.45

CloseOperation

0.45

 rând

0.45

magin

0.44

̈́

0.43

 Utilizamos

0.43

Gön

0.43

Activations Density 1.361%

technical terms related to experimental procedures or data analysis

No Comments

No Known Activations