INDEX

Explanations

formatted log messages and error responses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-mlp-65k

Configuration

google/gemma-scope-2b-pt-mlp/layer_18/width_65k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.18.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

LookAnd

-0.95

 autorytatywna

-0.93

AddTagHelper

-0.90

Efq

-0.88

 nahilalakip

-0.87

 Савезне

-0.86

ContentAsync

-0.85

TestingModule

-0.85

">//

-0.84

webElementXpaths

-0.83

POSITIVE LOGITS

Comp

0.42

COM

0.40

comp

0.40

Com

0.39

<strong>

0.38

can

0.38

av

0.36

 ujarnya

0.36

Activations Density 0.055%

formatted log messages and error responses

No Comments

No Known Activations