INDEX

Explanations

terms related to coefficients, particularly in mathematical or scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Jefus

-1.19

Personendaten

-1.18

 myſelf

-1.14

 Theſe

-1.11

 Anſ

-1.10

 Monfieur

-1.09

 Majefty

-1.09

 pleaſure

-1.01

GraphicsUnit

-1.01

 itſelf

-1.00

POSITIVE LOGITS

 Loss

0.67

 next

0.63

 loss

0.62

 LOSS

0.62

0.59

Loss

0.59

El

0.57

 asse

0.57

 losses

0.56

Activations Density 0.145%

terms related to coefficients, particularly in mathematical or scientific contexts

No Comments

No Known Activations