INDEX

Explanations

references to expressions 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 @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 NSCoder

-0.61

ChildScrollView

-0.57

currentColor

-0.55

quelize

-0.51

Width

-0.50

tură

-0.49

 Happens

-0.49

 Happen

-0.49

さすがに

-0.48

AsUp

-0.48

POSITIVE LOGITS

Expression

1.40

 Expression

1.10

 Expressions

1.07

Expressions

1.06

expression

0.96

expr

0.89

 expressions

0.87

expressions

0.86

Expr

0.82

 expression

0.81

Activations Density 0.138%

references to expressions in programming contexts

No Comments

No Known Activations