INDEX

Explanations

requests for help or information about specific issues, often with an emphasis on distinctions and doubt resolution

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

-0.46

 estekak

-0.45

 kasarigan

-0.44

mones

-0.43

魄

-0.42

bukkit

-0.42

BindingSource

-0.42

olism

-0.41

]-->

-0.41

 espir

-0.40

POSITIVE LOGITS

Any

1.25

any

1.21

Any

1.19

 whatsoever

1.17

 anybody

1.13

 apapun

1.08

ANY

1.06

 anyone

1.06

 Anywhere

1.04

anything

1.03

Activations Density 0.316%

requests for help or information about specific issues, often with an emphasis on distinctions and doubt resolution

No Comments

No Known Activations