INDEX

Explanations

assignments and initializations 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

rrggbb

-0.70

المناصب

-0.61

endforeach

-0.53

EClass

-0.52

__(/*!

-0.50

/**

-0.50

nach

-0.50

textAppearance

-0.49

 forward

-0.47

POSITIVE LOGITS

 null

1.06

null

0.95

 NULL

0.74

NULL

0.62

 nullptr

0.61

nil

0.58

 disponibilités

0.58

IUrlHelper

0.57

new

0.57

ylase

0.57

Activations Density 0.050%

assignments and initializations in code

No Comments

No Known Activations