INDEX

Explanations

terms related to switches and their operations

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

modelBuilder

-0.82

TintMode

-0.80

Portale

-0.73

 Partagez

-0.71

ologist

-0.69

 internetowa

-0.68

onAttach

-0.68

NewUrlParser

-0.68

afficheront

-0.67

 Reſ

-0.67

POSITIVE LOGITS

 switch

0.81

switch

0.77

 related

0.70

related

0.65

</tbody>

0.63

 SWITCH

0.61

 switches

0.57

SWITCH

0.56

 Switch

0.53

 Related

0.51

Activations Density 0.106%

terms related to switches and their operations

No Comments

No Known Activations