INDEX

Explanations

occurrences of numbers and mathematical terms or phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 kasarigan

-0.82

 InputDecoration

-0.74

脚注の使い方

-0.74

 للمعارف

-0.73

AndEndTag

-0.72

 FetchType

-0.71

ValueStyle

-0.70

webElementXpaths

-0.70

TintMode

-0.70

исленность

-0.70

POSITIVE LOGITS

 hundreds

0.68

 approximately

0.65

0.61

 dozens

0.60

0.58

 thousands

0.58

hundreds

0.57

 roughly

0.56

Activations Density 1.947%

occurrences of numbers and mathematical terms or phrases

No Comments

No Known Activations