INDEX

Explanations

terms related to formal, empirical, and quantitative analysis in a variety of contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 kaarangay

-0.74

GEBURTSDATUM

-0.69

IntoConstraints

-0.69

tagHelperRunner

-0.68

DOCTYPE

-0.67

+#+#

-0.65

PYX

-0.65

 समीक्षक

-0.63

TestingModule

-0.63

 للمعارف

-0.61

POSITIVE LOGITS

 olarak

0.76

 approach

0.73

 basis

0.72

적인

0.71

 answer

0.68

적으로

0.66

ized

0.66

 रूप

0.64

approach

0.61

 reasons

0.60

Activations Density 0.747%

terms related to formal, empirical, and quantitative analysis in a variety of contexts

No Comments

No Known Activations