INDEX

Explanations

occurrences of variable and function names in programming or code context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

RenderAtEndOf

-0.87

 فريبيس

-0.72

AndEndTag

-0.69

httphttps

-0.63

findpost

-0.60

 OFDb

-0.60

 SwitchCompat

-0.58

principalTable

-0.57

 BytesLike

-0.57

 IconData

-0.56

POSITIVE LOGITS

 ivelany

0.29

cu

0.25

drawiam

0.24

 respec

0.24

}*/

0.24

initiate

0.24

cipar

0.23

 coupes

0.23

pozdrawiam

0.23

fu

0.23

Activations Density 0.035%

occurrences of variable and function names in programming or code context

No Comments

No Known Activations