INDEX

Explanations

technical terms and identifiers, particularly related to gene studies or computational biology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_19/width_16k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.hook_mlp_out

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

 defaultstate

-0.66

lgari

-0.58

 propOrder

-0.56

 ब्रेकडाउन

-0.54

__)

-0.54

 ویکی‌پدی

-0.53

 digress

-0.53

#+#

-0.52

SourceChecksum

-0.50

StoryboardSegue

-0.50

POSITIVE LOGITS

tometer

0.52

rendon

0.51

tangentMode

0.50

rfc

0.50

===========

0.50

endphp

0.50

 Aussch

0.49

fastjson

0.49

AxisAlignment

0.48

setLevel

0.48

Activations Density 0.313%

technical terms and identifiers, particularly related to gene studies or computational biology

No Comments

No Known Activations