INDEX

Explanations

mathematical notations and symbols

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

Portale

-0.86

 levis

-0.81

 pleaſure

-0.80

 VizieR

-0.74

andaş

-0.74

 Aner

-0.74

 Barbar

-0.72

Menge

-0.71

oredCriteria

-0.71

>>>>>

-0.71

POSITIVE LOGITS

onAttach

0.66

esp

0.61

 fact

0.60

FTFY

0.60

kadang

0.60

âteau

0.59

ु

0.58

={`/

0.58

 Вт

0.55

Utf

0.54

Activations Density 0.096%

mathematical notations and symbols

No Comments

No Known Activations