INDEX

Explanations

references to academic or scientific journals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

IntoConstraints

-0.51

-0.47

 broder

-0.47

Encoded

-0.45

宙

-0.44

ạ

-0.43

ness

-0.42

POSITIVE LOGITS

 متعلقه

0.81

énéral

0.76

 cref

0.75

});*/

0.74

journal

0.74

Journal

0.72

 AspNetCore

0.71

 journaux

0.71

 Journal

0.69

setopt

0.69

Activations Density 0.635%

references to academic or scientific journals

No Comments

No Known Activations