INDEX

Explanations

method names that indicate getting or setting values 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 @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

-0.70

 iprot

-0.66

FontOfSize

-0.64

 propOrder

-0.64

RegistryLite

-0.62

UnknownFieldSet

-0.61

principalTable

-0.60

AccessorTable

-0.59

ItemLayout

-0.56

 wireType

-0.56

POSITIVE LOGITS

Portale

1.20

NUMX

0.78

0.77

 __('

0.76

ANT

0.73

_('

0.69

IATION

0.69

berglass

0.68

irie

0.68

CRR

0.67

Activations Density 0.051%

method names that indicate getting or setting values in code

No Comments

No Known Activations