INDEX

Explanations

specific numerical codes or identifiers related to data structures or programming configurations

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

 كومونز

-1.03

bootstrapcdn

-0.95

AsUp

-0.92

 MainAxisSize

-0.91



-0.90

$_(

-0.88

CloseOperation

-0.86

 ARXIV

-0.84

✭✭

-0.83

EDEFAULT

-0.83

POSITIVE LOGITS

↵↵

0.65

0.60

0.58

0.56

0.51

↵↵↵↵

0.50

↵

0.48

</b>

0.48

<eos>

0.48

Activations Density 1.674%

specific numerical codes or identifiers related to data structures or programming configurations

No Comments

No Known Activations