INDEX

Explanations

references to information dissemination and media reports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 swear

-0.47

 velours

-0.47

EditorBrowsable

-0.46

npr

-0.45

NPR

-0.44

Gott

-0.43

NPR

-0.43

 Riks

-0.43

 Debe

-0.43

 textStatus

-0.42

POSITIVE LOGITS

PerformLayout

0.97

timewa

0.69

Hentet

0.66

 kasarigan

0.66

KommentareTeilen

0.64

 sumpay

0.62

sizeCache

0.61

 oper

0.61

 AssemblyCulture

0.60

 tartalomajánló

0.58

Activations Density 0.078%

references to information dissemination and media reports

No Comments

No Known Activations