INDEX

Explanations

technical terms and operations related to programming and system commands

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

 itſelf

-0.85

 myſelf

-0.82

 فريبيس

-0.80

Personensuche

-0.78

 Reſ

-0.77

IsMutable

-0.76

sizeCache

-0.76

 raiſ

-0.75

 nahilalakip

-0.75

MessageState

-0.73

POSITIVE LOGITS

0.66

de

0.62

di

0.60

van

0.60

0.59

0.55

0.53

0.52

Activations Density 0.482%

technical terms and operations related to programming and system commands

No Comments

No Known Activations