INDEX

Explanations

instructions or tips related to organization and preparation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

toHave

-0.61

 supuestamente

-0.59

ďaka

-0.59

almost

-0.58

 milliers

-0.58

Almost

-0.57

 Almost

-0.57

epam

-0.56

 tragically

-0.56

maktadır

-0.54

POSITIVE LOGITS

 whatever

0.95

 whichever

0.92

 atleast

0.90

 möglichst

0.85

 yourself

0.83

 plenty

0.82

 enough

0.81

 almeno

0.81

 appropriate

0.80

 preferably

0.79

Activations Density 0.485%

instructions or tips related to organization and preparation

No Comments

No Known Activations