INDEX

Explanations

terms and phrases related to documentation and disclosure processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

Tikang

-0.98

ThroughAttribute

-0.88

новниш

-0.85

__':

-0.76

__":

-0.76

uxxxx

-0.68

Sucesor

-0.68



-0.67

 незавершена

-0.66

 Савезне

-0.66

POSITIVE LOGITS

 document

0.86

 documents

0.75

 copy

0.67

pdf

0.65

 copies

0.64

📄

0.64

📜

0.63

documents

0.63

这份

0.62

一份

0.61

Activations Density 0.800%

terms and phrases related to documentation and disclosure processes

No Comments

No Known Activations