INDEX

Explanations

class and method definitions in Java

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 pianos

-0.59

 neceffary

-0.59

 Jefus

-0.58

ſy

-0.57

 Maulana

-0.57

 poffible

-0.56

 becauſe

-0.56

 faſt

-0.56

 unum

-0.56

 Clau

-0.55

POSITIVE LOGITS

IBOutlet

0.69

PathVariable

0.63

ViewChild

0.62

InjectAttribute

0.62

 كومونز

0.60

MethodManager

0.59

Rhestr

0.59

Composable

0.59

IBAction

0.56

 complètes

0.56

Activations Density 0.035%

class and method definitions in Java

No Comments

No Known Activations