INDEX

Explanations

terms and phrases related to records and documentation

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

-0.70

yargs

-0.65

Искәрмәләр

-0.63

addWidget

-0.60

 Процитовано

-0.59

DoubleQuotes

-0.59

featureID

-0.58

ienki

-0.57

RepeatedField

-0.57

pherals

-0.56

POSITIVE LOGITS

keeping

0.86

atorios

0.75

breaking

0.74

book

0.71

setting

0.68

keeper

0.67

atorio

0.67

 breaking

0.67

 books

0.64

nungs

0.63

Activations Density 0.125%

terms and phrases related to records and documentation

No Comments

No Known Activations