INDEX

Explanations

references to various sections or components within texts

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

jsxFileName

-0.51

 Worcester

-0.43

号

-0.41

ma

-0.41

まま

-0.41

 Faul

-0.41

owieck

-0.41

El

-0.40

-0.39

Ba

-0.39

POSITIVE LOGITS

 typelib

0.94

 виправивши

0.80

 ostavi

0.80

 ofthe

0.76

ofthe

0.70

новниш

0.70

Демографія

0.70



0.70

Legături

0.68

 Audiodateien

0.67

Activations Density 0.326%

references to various sections or components within texts

No Comments

No Known Activations