INDEX

Explanations

terms related to obscurity and the unknown

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

bootstrapcdn

-0.75

oa̍t

-0.61

makeConstraints

-0.60

MemoryWarning

-0.57

tonsoft

-0.57

شهاد

-0.54

ModelState

-0.53

PhysRevD

-0.53

lusconi

-0.51

itzende

-0.51

POSITIVE LOGITS

 obscure

0.95

 obscurity

0.92

forgotten

0.86

 forgotten

0.81

obscure

0.80

 seldom

0.72

 underrated

0.72

 overlooked

0.71

 unnoticed

0.70

 oubli

0.70

Activations Density 0.263%

terms related to obscurity and the unknown

No Comments

No Known Activations