INDEX

Explanations

references to data models and structures within code

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

 bezeichneter

-0.67

pushFollow

-0.61

antMatchers

-0.60

KeySpec

-0.59

SuppressLint

-0.58

entid

-0.58

GEBURTSDATUM

-0.57

<bos>

-0.57

Fatalf

-0.55

 transférez

-0.55

POSITIVE LOGITS

ysacchar

0.60

cellaneous

0.52

fromnode

0.51

 تانيه

0.49

śnia

0.46

НОСТИ

0.45

 సౌకర్య

0.45

quième

0.45

 Panchayat

0.44

 Polis

0.44

Activations Density 0.130%

references to data models and structures within code

No Comments

No Known Activations