INDEX

Explanations

Java import statements and class definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

AddTagHelper

-0.85

transQ

-0.85

WriteTagHelper

-0.81

 Normdatei

-0.78

RegressionTest

-0.75

PreferredItem

-0.74

lccn

-0.70

ValueStyle

-0.70

 &___

-0.69

 Infórmanos

-0.66

POSITIVE LOGITS

 nube

0.48

("../

0.41

 pratic

0.41

haupt

0.41

 mult

0.41

punct

0.40

 parabolic

0.38

 лю

0.38

enx

0.38

 آوری

0.38

Activations Density 0.057%

Java import statements and class definitions

No Comments

No Known Activations