INDEX

Explanations

terms related to processes and procedures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Roskov

-0.83

DoubleQuotes

-0.83

TestingModule

-0.66

IntoConstraints

-0.61

 AssemblyProduct

-0.60

mpotent

-0.59

Personensuche

-0.59

 tampoco

-0.56

 infeliz

-0.56

 Obrador

-0.55

POSITIVE LOGITS

SupportActionBar

0.56

}]

0.52

"¡

0.52

要在

0.52

risse

0.51

mella

0.50

setContentView

0.50

 mark

0.50

 people

0.49

 Chapitre

0.48

Activations Density 0.527%

terms related to processes and procedures

No Comments

No Known Activations