INDEX

Explanations

function-related expressions

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

suri

-0.53

 Swiss

-0.48

-0.46

 techo

-0.46

se

-0.45

 opinion

-0.45

Er

-0.44

su

-0.44

ześnie

-0.43

 program

-0.43

POSITIVE LOGITS

 resourceCulture

1.12

StoryboardSegue

1.01

expandindo

0.94

GEBURTSDATUM

0.91

 linkovi

0.91

Collegamenti

0.89

awaiter

0.89

UnusedPrivate

0.88

SharedCtor

0.87

LookAnd

0.85

Activations Density 0.053%

function-related expressions

No Comments

No Known Activations