INDEX

Explanations

technical terminology and formal definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

LookAnd

-0.92

IUrlHelper

-0.85

tvguidetime

-0.75

NewGuid

-0.69

ьаж

-0.66

QMetaType

-0.66

 jScrollPane

-0.65

<tfoot>

-0.61

 wireType

-0.60

TestBed

-0.60

POSITIVE LOGITS

 below

0.94

 listed

0.80

 above

0.78

 discussed

0.78

 described

0.78

 mentioned

0.76

 outlined

0.76

 following

0.73

below

0.72

described

0.68

Activations Density 1.135%

technical terminology and formal definitions

No Comments

No Known Activations