INDEX

Explanations

concepts related to testing and debugging

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

KommentareTeilen

-0.79

IsMutable

-0.76

NegativeButton

-0.74

ChildScrollView

-0.69

AccessorTable

-0.69

PerformLayout

-0.68

 onPostExecute

-0.66

dataclass

-0.64

$_['

-0.61

BASEPATH

-0.60

POSITIVE LOGITS

 experiment

0.75

 purposes

0.65

 experimental

0.65

 experiments

0.64

 Purposes

0.63

 Experiment

0.62

 experimentation

0.62

 testing

0.60

Experiment

0.58

 experimenting

0.58

Activations Density 0.646%

concepts related to testing and debugging

No Comments

No Known Activations