INDEX

Explanations

error codes and programming-related terminology

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Personensuche

-0.81

interopRequire

-0.77

IndentedString

-0.74

 Exactos

-0.73

 gainera

-0.71

Morfo

-0.71

styleType

-0.69

SharedCtor

-0.69

 noDo

-0.68

EFE

-0.68

POSITIVE LOGITS

 runnable

0.61

 calendriers

0.57

bra

0.56

取

0.54

nons

0.54

 namelijk

0.53

Delayed

0.52

rist

0.51

getString

0.51

odzi

0.51

Activations Density 2.988%

error codes and programming-related terminology

No Comments

No Known Activations