INDEX

Explanations

symbols and operators typically used in coding or mathematical expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

__":

-0.75

CppMethod

-0.72

openzeppelin

-0.71

bootstrapcdn

-0.71

__':

-0.70

ⓧ

-0.66

__":

-0.64

BeginContext

-0.63

Naissance

-0.63

scriptcase

-0.62

POSITIVE LOGITS

/−

0.94

&+

0.87

_+

0.83

++++++++++++++++

0.83

","+

0.68

/-

0.66

++++++++

0.65

":"+

0.65

---+

0.64

ve

0.63

Activations Density 0.504%

symbols and operators typically used in coding or mathematical expressions

No Comments

No Known Activations