INDEX

Explanations

terms related to normality and regularity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

IntoConstraints

-0.83

 myö

-0.75

seamnă

-0.73

 désol

-0.68

LookAnd

-0.66

WithIOException

-0.66

 ModelExpression

-0.65

 înc

-0.64

PutMapping

-0.63

 nakalista

-0.62

POSITIVE LOGITS

 regular

0.67

Regular

0.64

 Regular

0.63

 pure

0.58

 actual

0.58

regular

0.57

 straight

0.57

 legit

0.57

 normal

0.55

 formal

0.54

Activations Density 0.432%

terms related to normality and regularity

No Comments

No Known Activations