INDEX

Explanations

references to formal validation processes or requirements

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

Code, links, or interfaces

np_acts-logits-general · gemini-2.0-flash

code related to data or configuration

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

zional

-0.53

<bos>

-0.51

 hâte

-0.49

zwischen

-0.47

 drôle

-0.47

 bestanden

-0.46

Personendaten

-0.46

 urme

-0.46

 aussitôt

-0.46

 protoimpl

-0.45

POSITIVE LOGITS

PerformLayout

0.77

AddTagHelper

0.71

0.68

ConstraintMaker

0.64

readAs

0.57

mybatisplus

0.57

apimachinery

0.56

(:

0.55

CppMethod

0.54

makeConstraints

0.54

Activations Density 0.153%

references to formal validation processes or requirements

Code, links, or interfaces

code related to data or configuration

No Comments

No Known Activations