INDEX

Explanations

instances of interjections or conversational markers indicating a response

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

URLException

-0.84

IntoConstraints

-0.83

EDEFAULT

-0.82

 AssemblyCulture

-0.81

HostException

-0.80

anjutan

-0.80

 Normdatei

-0.80

 ويكيميديا

-0.79

expandindo

-0.78

webElement

-0.77

POSITIVE LOGITS

my

0.57

No

0.53

0.51

no

0.51

My

0.51

":

0.50

”:

0.49

What

0.48

mu

0.48

 colpa

0.48

Activations Density 0.179%

instances of interjections or conversational markers indicating a response

No Comments

No Known Activations