INDEX

Explanations

patterns of numbers and symbols typically associated with code or data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.41.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

 оригіналу

-0.52

awtextra

-0.41

__.__

-0.38

Jeografia

-0.37

 архивлан

-0.37

ENDIX

-0.36

 oversee

-0.35

 AssemblyCulture

-0.35

 Kron

-0.35

 frost

-0.33

POSITIVE LOGITS

0.79

0.50

0.46

 umě

0.41

PasswordEncoder

0.40

 eletrônico

0.40

 saurait

0.39

发表于

0.38

 anch

0.37

uxxxx

0.37

Activations Density 0.080%

patterns of numbers and symbols typically associated with code or data structures

No Comments

No Known Activations