INDEX

Explanations

references to documents 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 @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

withIdentifier

-0.99

帖最后由

-0.94

mergeFrom

-0.93

styleUrls

-0.89

SBATCH

-0.85

Viitteet

-0.80

 Theſe

-0.78

GenerationType

-0.77

 réguli

-0.77

fjspx

-0.76

POSITIVE LOGITS

 documents

2.33

 document

2.25

 Document

2.13

 Documents

2.04

documents

2.03

document

1.93

Document

1.93

Documents

1.85

 DOCUMENT

1.81

 Dokument

1.75

Activations Density 0.071%

references to documents and documentation

No Comments

No Known Activations