INDEX

Explanations

concepts related to machine learning models and their components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

✨:

-0.69

Obrázky

-0.63

 createSlice

-0.63

KEYCODE

-0.61

 sauvages

-0.60

IBarButtonItem

-0.59

 imageNamed

-0.59

AndEndTag

-0.58

TagMode

-0.58

astify

-0.57

POSITIVE LOGITS

 trained

0.67

trained

0.62

 sklearn

0.61

keras

0.57

 learning

0.57

 training

0.56

 Machine

0.55

Machine

0.55

Trained

0.55

 machine

0.55

Activations Density 0.797%

concepts related to machine learning models and their components

No Comments

No Known Activations