INDEX

Explanations

occurrences of the letter 'a' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Personendaten

-0.80

Germain

-0.78

 مشين

-0.77

 autorytatywna

-0.74

theless

-0.72

jména

-0.72

 publick

-0.71

 Disqus

-0.69

 contextLoads

-0.69

 iſt

-0.68

POSITIVE LOGITS

to

0.86

Σε

0.80

TO

0.75

à

0.75

DotNetBar

0.71

 σε

0.70

 به

0.69

 BorderRadius

0.68

zu

0.68

the

0.68

Activations Density 0.020%

occurrences of the letter 'a' in various contexts

No Comments

No Known Activations