INDEX

Explanations

function or method definitions in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

ekš

-0.51

 הרי

-0.46

RenderAtEndOf

-0.45

 diet

-0.45

DispatchToProps

-0.45

ReusableCell

-0.45

خوش

-0.44

ViewStyle

-0.43

SizeF

-0.43

toContain

-0.43

POSITIVE LOGITS

enumi

0.77

 públicas

0.70

});*/

0.70

public

0.70

 public

0.66

 pública

0.63

ritsar

0.61

})*/

0.61

 públicos

0.60

 publiques

0.60

Activations Density 0.023%

function or method definitions in code

No Comments

No Known Activations