INDEX

Explanations

references to academic publishing and documentation, especially related to software and licensing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

CodedInputStream

-0.72

StandardCharsets

-0.68

 informée

-0.66

DockStyle

-0.66

cambrian

-0.63

endregion

-0.62

 Realt

-0.60

audiovisuel

-0.60

 suun

-0.59

 Pareto

-0.59

POSITIVE LOGITS

pyx

4.43

Pyx

1.86

PYX

0.92

 <<<<<<<<<<<<<<

0.86

 CYTHON

0.82

scriptcase

0.74

tagHelper

0.73

 متعلقه

0.70

 PyObject

0.67

 مؤرشف

0.67

Activations Density 0.010%

references to academic publishing and documentation, especially related to software and licensing

No Comments

No Known Activations