INDEX

Explanations

references to events and organizational decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_mlp_out

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

 ComVisible

-0.73

Brainz

-0.62

脚注の使い方

-0.61

 handleMessage

-0.60

Datuak

-0.58

 gyhoeddwyd

-0.56

sidemargin

-0.56

تقاوى

-0.56

Personensuche

-0.55

cense

-0.55

POSITIVE LOGITS

 ahead

0.83

ahead

0.77

 AHEAD

0.73

 Ahead

0.66

Ahead

0.63

Hochspringen

0.59

stdc

0.57

 andato

0.57

 épaules

0.57

go

0.56

Activations Density 0.173%

references to events and organizational decisions

No Comments

No Known Activations