INDEX

Explanations

mathematical expressions and notation

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

AddTagHelper

-0.90

ArrowToggle

-0.83

 ویکی‌پدی

-0.77

évaluateur

-0.77

GEBURTSDATUM

-0.75

 betweenstory

-0.75

BeginContext

-0.74

QMetaType

-0.71

principalTable

-0.71

 AspNetCore

-0.70

POSITIVE LOGITS

 Mots

0.42

rettet

0.37

ссор

0.36

ónia

0.36

 Nếu

0.36

SHIPPING

0.35

 potential

0.35

Dot

0.35

 stratégies

0.35

FormState

0.34

Activations Density 0.246%

mathematical expressions and notation

No Comments

No Known Activations