INDEX

Explanations

references to forms and documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 متعلقه

-0.91

rungsseite

-0.87

nî

-0.85

SpringRunner

-0.84

 ویکی‌پدیا

-0.83

 Pliocene

-0.76

verifyException

-0.74

下载附件

-0.72

MemoryWarning

-0.71

JNIEnv

-0.71

POSITIVE LOGITS

 Form

4.59

Form

4.55

 FORM

3.93

 form

3.90

form

3.81

FORM

3.48

 Forms

3.31

 forms

3.08

forms

2.92

Forms

2.83

Activations Density 0.097%

references to forms and documentation

No Comments

No Known Activations