INDEX

Explanations

high levels of numerical data or specific expressions in mathematical or technical writing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

Portály

-0.72

verwijspagina

-0.71

 通販

-0.71

%%

-0.69

 Lovato

-0.67

 становника

-0.67

 Lumpur

-0.66

Архівовано

-0.65

]]

-0.65

pyplot

-0.64

POSITIVE LOGITS

 Francine

0.70

\{\\

0.70

 anledning

0.69

<blockquote>

0.67

 hoods

0.67

 <<<<<<<<<<<<<<

0.66

 ää

0.66

 Franks

0.65

 podoba

0.65

 republics

0.64

Activations Density 0.010%

high levels of numerical data or specific expressions in mathematical or technical writing

No Comments

No Known Activations