INDEX

Explanations

function and event-related programming constructs

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

uğ

-0.45

 errno

-0.43

terus

-0.43

šķ

-0.42

 taşı

-0.41

dą

-0.40

ớm

-0.40

 sớm

-0.39

engo

-0.39

Mistake

-0.39

POSITIVE LOGITS

GEBURTSDATUM

0.82

 Roskov

0.79

UserScript

0.78

complexContent

0.76

ագրություններ

0.76

Personensuche

0.74

 שוליים

0.73

 function

0.70

Przypisy

0.69

 lambda

0.69

Activations Density 0.157%

function and event-related programming constructs

No Comments

No Known Activations