INDEX

Explanations

references to academic or literary works

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

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

__(/*!

-0.56

 CreateTagHelper

-0.55

 unknownFields

-0.55

CodeDom

-0.53

 ErrIntOverflow

-0.53

 Lightboxes

-0.53

erialization

-0.53

 }}"></

-0.52

awtextra

-0.51

djangoproject

-0.51

POSITIVE LOGITS

 title

3.60

title

3.13

 Title

3.03

 titles

2.95

Title

2.89

 TITLE

2.79

TITLE

2.67

 título

2.61

 titel

2.51

 Titles

2.47

Activations Density 0.344%

references to academic or literary works

No Comments

No Known Activations