INDEX

Explanations

terms associated with filtering and data processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

 pyruvate

-0.92

nextProps

-0.91

 للاسماء

-0.87

WebVitals

-0.86

ymce

-0.85

 متعلقه

-0.85

onedDateTime

-0.83

 elettrica

-0.82

ruvate

-0.82

+#+#

-0.82

POSITIVE LOGITS

 filters

1.91

 filter

1.82

 Filter

1.71

filters

1.71

 Filters

1.71

Filter

1.68

filter

1.66

 FILTER

1.61

Filters

1.61

FILTER

1.54

Activations Density 0.086%

terms associated with filtering and data processing

No Comments

No Known Activations