INDEX

Explanations

references to percentages and statistical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 démocr

-0.68

 ibunya

-0.66

 sentiers

-0.65

 exemplaires

-0.64

 pouvoirs

-0.63

 côtés

-0.61

нез

-0.61

 sœurs

-0.61

 bâtiments

-0.60

 épaules

-0.59

POSITIVE LOGITS

 lenker

0.81

RenderAtEndOf

0.74

 snippetHide

0.74

zości

0.73

 propOrder

0.73

 collectons

0.71

GEBURTSDATUM

0.71

 שוליים

0.71

 חיצוניים

0.70

 كومونز

0.69

Activations Density 0.393%

references to percentages and statistical data

No Comments

No Known Activations