INDEX

Explanations

numerical values and variable indices, particularly in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 assurent

-0.60

发表于

-0.49

 sợi

-0.48

RenderAtEndOf

-0.48

essment

-0.46

 nguồn

-0.45

-0.44

 guiding

-0.44

 Afterwards

-0.43

))[

-0.43

POSITIVE LOGITS

AnchorStyles

0.92

 MainAxisSize

0.82

AdapterFactory

0.77

rhosis

0.73

//

0.71

 Roskov

0.71

 ThemeData

0.69

sidemargin

0.69

^(@)

0.69

antaranya

0.69

Activations Density 0.250%

numerical values and variable indices, particularly in programming contexts

No Comments

No Known Activations